dealignai/GLM-5.3-Flash-UNCENSORED-FP8
zetlyn/models-hf model hf dealignai/GLM-5.3-Flash-UNCENSORED-FP8 known 2026-08-26
https://huggingface.co/dealignai/GLM-5.3-Flash-UNCENSORED-FP8
Properties
| author | dealignaireceipt
What the source handed over{
"_asked": "dealignai/GLM-5.3-Flash-UNCENSORED-FP8",
"_id": "6a8f5600e8e799f3299d529f",
"author": "dealignai",
"cardData": {
"base_model": [
"zai-org/GLM-5.3-Flash"
],
"language": [
"en"
],
"license": "mit",
"tags": [
"abliterated",
"uncensored",
"crack",
"glm",
"moe",
"fp8",
"vision",
"mtp"
],
"thumbnail": "dealign_mascot.png"
},
"config": {
"architectures": [
"Glm5NextForConditionalGeneration"
],
"chat_template_jinja": "[gMASK]<sop>\n{%- set effective_reasoning_effort = reasoning_effort if reasoning_effort is defined and reasoning_effort in ['low', 'high'] else 'max' -%}\n{%- if effective_reasoning_effort is not none -%}<|system|>Reasoning Effort: {{ effective_reasoning_effort | capitalize }}{%- endif -%}\n{%- set clear_thinking = clear_thinking if clear_thinking is defined else true -%}\n{%- if tools -%}\n{%- macro tool_to_json(tool) -%}\n {%- set ns_tool = namespace(first=true) -%}\n {{ '{' -}}\n {%- for k, v in tool.items() -%}\n {%- if k != 'defer_loading' and k != 'strict' -%}\n {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}\n {%- set ns_tool.first = false -%}\n \"{{ k }}\": {{ v | tojson(ensure_ascii=False) }}\n {%- endif -%}\n {%- endfor -%}\n {{- '}' -}}\n{%- endmacro -%}\n{%- macro tool_references_to_response(refs) -%}\n {{- '<tool_response><tools>\\n' -}}\n {%- for tr in refs -%}\n {%- for tool in tools -%}\n {%- if 'function' in tool -%}\n {%- set tool = tool['function'] -%}\n {%- endif -%}\n {%- if tool.name == tr.name -%}\n {{- tool_to_json(tool) + '\\n' -}}\n {%- endif -%}\n {%- endfor -%}\n {%- endfor -%}\n {{- '</tools></tool_response>' -}}\n{%- endmacro -%}\n<|system|>\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{% for tool in tools %}\n{%- if 'function' in tool -%}\n {%- set tool = tool['function'] -%}\n{%- endif -%}\n{% if tool.defer_loading is not defined or not tool.defer_loading %}\n{{ tool_to_json(tool) }}\n{% endif %}\n{% endfor %}\n</tools>\n\nFor each function call, output the function name and arguments within the following XML format:\n<tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}\n{%- macro emit_image() -%}<|begin_of_image|><|image|><|end_of_image|>{%- endmacro -%}\n{%- macro emit_video() -%}<|begin_of_video|><|video|><|end_of_video|>{%- endmacro -%}\n{%- macro emit_audio() -%}<|begin_of_audio|><|end_of_audio|>{%- endmacro -%}\n{%- macro visible_text(content) -%}\n {%- if content is string -%}\n {{- content -}}\n {%- elif content is iterable and content is not mapping -%}\n {%- for item in content -%}\n {%- if item is mapping and item.type == 'text' -%}\n {{- item.text -}}\n {%- elif item is string -%}\n {{- item -}}\n {%- elif item is mapping and item.type in ['image', 'image_url'] -%}\n {{- emit_image() -}}\n {%- elif item is mapping and item.type in ['video', 'video_url'] -%}\n {{- emit_video() -}}\n {%- elif item is mapping and item.type in ['audio', 'audio_url', 'input_audio'] -%}\n {{- emit_audio() -}}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{- content }}\n {%- endif -%}\n{%- endmacro -%}\n{%- macro tool_response(text) -%}\n{{- '<tool_response>' + text + '</tool_response>' -}}\n{%- endmacro -%}\n{%- macro render_tool_response(m) -%}\n{%- if m.content is string -%}\n {{- tool_response(m.content) -}}\n{%- elif m.content and m.content is not mapping and m.content.0.type == \"tool_reference\" -%}\n {{- tool_references_to_response(m.content) -}}\n{%- elif is_list_of_outputs(m) -%}\n {%- for tr in m.content -%}\n {%- if tr.output is iterable and tr.output is not string and tr.output is not mapping and tr.output and tr.output.0.type == \"tool_reference\" -%}\n {{- tool_references_to_response(tr.output) -}}\n {%- else -%}\n {{- tool_response(visible_text(tr.output)) -}}\n {%- endif -%}\n {%- endfor -%}\n{%- else -%}\n {{- tool_response(visible_text(m.content)) -}}\n{%- endif -%}\n{%- endmacro -%}\n{%- macro id_of(obj) -%}\n {%- if obj.tool_call_id -%}\n {{- obj.tool_call_id -}}\n {%- elif obj.id -%}\n {{- obj.id -}}\n {%- endif -%}\n{%- endmacro -%}\n{%- macro is_list_of_outputs(m) -%}\n {%- if m.content and m.content.0.output is defined -%}1{%- endif -%}\n{%- endmacro -%}\n{%- macro has_dup_tool_result_id(lo, hi, target) -%}\n {%- set ns_cnt = namespace(n=0) -%}\n {%- for k in range(lo, hi + 1) -%}\n {%- set m = messages[k] -%}\n {%- if is_list_of_outputs(m) -%}\n {%- for entry in m.content -%}\n {%- if id_of(entry) == target -%}\n {%- set ns_cnt.n = ns_cnt.n + 1 -%}\n {%- endif -%}\n {%- endfor -%}\n {%- elif id_of(m) == target -%}\n {%- set ns_cnt.n = ns_cnt.n + 1 -%}\n {%- endif -%}\n {%- if ns_cnt.n > 1 -%}{%- break -%}{%- endif -%}\n {%- endfor -%}\n {%- if ns_cnt.n > 1 -%}1{%- endif -%}\n{%- endmacro -%}\n{%- macro tc_id_exists(tcs, target) -%}\n {%- set ns_f = namespace(found=false) -%}\n {%- for tc in tcs -%}\n {%- if id_of(tc) == target -%}\n {%- set ns_f.found = true -%}\n {%- break -%}\n {%- endif -%}\n {%- endfor -%}\n {%- if ns_f.found -%}1{%- endif -%}\n{%- endmacro -%}\n{%- set ns = namespace(last_user_index=-1) -%}\n{%- for m in messages %}\n {%- if m.role == 'user' %}\n {%- set ns.last_user_index = loop.index0 -%}\n {%- endif %}\n{%- endfor %}\n{%- for m in messages -%}\n{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}\n{%- elif m.role == 'assistant' -%}\n<|assistant|>\n{%- set content = visible_text(m.content) %}\n{%- if m.reasoning_content is string %}\n {%- set reasoning_content = m.reasoning_content %}\n{%- elif '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}\n {%- set content = content.split('</think>')[-1] %}\n{%- endif %}\n{%- if (not clear_thinking or loop.index0 > ns.last_user_index) and reasoning_content is defined -%}\n{{ '<think>' + reasoning_content + '</think>'}}\n{%- else -%}\n{{ '<think></think>' }}\n{%- endif -%}\n{%- if content.strip() -%}\n{{ content.strip() }}\n{%- endif -%}\n{% if m.tool_calls %}\n{% for tc in m.tool_calls %}\n{%- if tc.function %}\n {%- set tc = tc.function %}\n{%- endif %}\n{{- '<tool_call>' + tc.name -}}\n{% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}\n{% endif %}\n{%- elif m.role == 'tool' -%}\n{%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|observation|>' -}}\n {%- set block_start = loop.index0 -%}\n {%- set ns_blk = namespace(end=block_start) -%}\n {%- for j in range(block_start, messages|length) -%}\n {%- if messages[j].role == 'tool' -%}\n {%- set ns_blk.end = j -%}\n {%- else -%}\n {%- break -%}\n {%- endif -%}\n {%- endfor -%}\n {%- set ns_a = namespace(tool_calls=none) -%}\n {%- if block_start > 0 and messages[block_start - 1].role == 'assistant' and messages[block_start - 1].tool_calls -%}\n {%- set ns_a.tool_calls = messages[block_start - 1].tool_calls -%}\n {%- endif -%}\n {%- set ns_chk = namespace(can_sort=true) -%}\n {%- if not ns_a.tool_calls -%}\n {%- set ns_chk.can_sort = false -%}\n {%- else -%}\n {%- for k in range(block_start, ns_blk.end + 1) -%}\n {%- set m = messages[k] -%}\n {%- if is_list_of_outputs(m) -%}\n {%- for entry in m.content -%}\n {%- set eid = id_of(entry) -%}\n {%- if not eid -%}\n {%- set ns_chk.can_sort = false -%}\n {%- elif has_dup_tool_result_id(block_start, ns_blk.end, eid) -%}\n {%- set ns_chk.can_sort = false -%}\n {%- elif not tc_id_exists(ns_a.tool_calls, eid) -%}\n {%- set ns_chk.can_sort = false -%}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {%- set tk_id = id_of(m) -%}\n {%- if not tk_id -%}\n {%- set ns_chk.can_sort = false -%}\n {%- elif has_dup_tool_result_id(block_start, ns_blk.end, tk_id) -%}\n {%- set ns_chk.can_sort = false -%}\n {%- elif not tc_id_exists(ns_a.tool_calls, tk_id) -%}\n {%- set ns_chk.can_sort = false -%}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n {%- for i in range(ns_a.tool_calls | length) -%}\n {%- set tc_id = id_of(ns_a.tool_calls[i]) -%}\n {%- if not tc_id -%}\n {%- set ns_chk.can_sort = false -%}\n {%- endif -%}\n {%- for j in range(i + 1, ns_a.tool_calls | length) -%}\n {%- if id_of(ns_a.tool_calls[j]) == tc_id -%}\n {%- set ns_chk.can_sort = false -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endfor -%}\n {%- endif -%}\n {%- if ns_chk.can_sort -%}\n {%- for tc in ns_a.tool_calls -%}\n {%- set tc_id = id_of(tc) -%}\n {%- for k in range(block_start, ns_blk.end + 1) -%}\n {%- set m = messages[k] -%}\n {%- if is_list_of_outputs(m) -%}\n {%- for entry in m.content -%}\n {%- set eid = id_of(entry) -%}\n {%- if eid == tc_id -%}\n {%- if entry.output is iterable and entry.output is not string and entry.output is not mapping and entry.output and entry.output.0.type == \"tool_reference\" -%}\n {{- tool_references_to_response(entry.output) -}}\n {%- else -%}\n {{- tool_response(visible_text(entry.output)) -}}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n{%- else -%}\n {%- set tk_id = id_of(m) -%}\n {%- if tk_id == tc_id -%}\n {{- render_tool_response(m) -}}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endfor -%}\n {%- else -%}\n {%- for k in range(block_start, ns_blk.end + 1) -%}\n {{- render_tool_response(messages[k]) -}}\n {%- endfor -%}\n {%- endif -%}\n{% endif -%}\n{%- elif m.role == 'system' -%}\n<|system|>{{ visible_text(m.content) }}\n{%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n <|assistant|>{{- '<think>' -}}\n{%- endif -%}\n",
"model_type": "glm5_next",
"quantization_config": {
"modules_to_not_convert": [
"attn_mha",
"attn_mqa",
"dt_bias",
"hyper_connection",
"lm_head",
"mapping_proj",
"model.embed_tokens",
"model.layers.0.hc_attn_base",
"model.layers.0.hc_attn_fn",
"model.layers.0.hc_attn_scale",
"model.layers.0.hc_ffn_base",
"model.layers.0.hc_ffn_fn",
"model.layers.0.hc_ffn_scale",
"model.layers.0.input_layernorm",
"model.layers.0.post_attention_layernorm",
"model.layers.0.self_attn.A_log",
"model.layers.0.self_attn.b_proj",
"model.layers.0.self_attn.dt_bias",
"model.layers.0.self_attn.f_a_proj",
"model.layers.0.self_attn.f_b_proj",
"model.layers.0.self_attn.fused_qkvbfg_a_proj",
"model.layers.0.self_attn.g_a_proj",
"model.layers.0.self_attn.g_b_proj",
"model.layers.0.self_attn.k_conv1d",
"model.layers.0.self_attn.k_proj",
"model.layers.0.self_attn.o_norm",
"model.layers.0.self_attn.o_proj",
"model.layers.0.self_attn.q_conv1d",
"model.layers.0.self_attn.q_proj",
"model.layers.0.self_attn.qkv_proj",
"model.layers.0.self_attn.v_conv1d",
"model.layers.0.self_attn.v_proj",
"model.layers.1.hc_attn_base",
"model.layers.1.hc_attn_fn",
"model.layers.1.hc_attn_scale",
"model.layers.1.hc_ffn_base",
"model.layers.1.hc_ffn_fn",
"model.layers.1.hc_ffn_scale",
"model.layers.1.input_layernorm",
"model.layers.1.post_attention_layernorm",
"model.layers.1.self_attn.A_log",
"model.layers.1.self_attn.b_proj",
"model.layers.1.self_attn.dt_bias",
"model.layers.1.self_attn.f_a_proj",
"model.layers.1.self_attn.f_b_proj",
"model.layers.1.self_attn.fused_qkvbfg_a_proj",
"model.layers.1.self_attn.g_a_proj",
"model.layers.1.self_attn.g_b_proj",
"model.layers.1.self_attn.k_conv1d",
"model.layers.1.self_attn.k_proj",
"model.layers.1.self_attn.o_norm",
"model.layers.1.self_attn.o_proj",
"model.layers.1.self_attn.q_conv1d",
"model.layers.1.self_attn.q_proj",
"model.layers.1.self_attn.qkv_proj",
"model.layers.1.self_attn.v_conv1d",
"model.layers.1.self_attn.v_proj",
"model.layers.10.hc_attn_base",
"model.layers.10.hc_attn_fn",
"model.layers.10.hc_attn_scale",
"model.layers.10.hc_ffn_base",
"model.layers.10.hc_ffn_fn",
"model.layers.10.hc_ffn_scale",
"model.layers.10.input_layernorm",
"model.layers.10.mlp.gate",
"model.layers.10.mlp.gate.e_score_correction_bias",
"model.layers.10.post_attention_layernorm",
"model.layers.10.self_attn.A_log",
"model.layers.10.self_attn.b_proj",
"model.layers.10.self_attn.dt_bias",
"model.layers.10.self_attn.f_a_proj",
"model.layers.10.self_attn.f_b_proj",
"model.layers.10.self_attn.fused_qkvbfg_a_proj",
"model.layers.10.self_attn.g_a_proj",
"model.layers.10.self_attn.g_b_proj",
"model.layers.10.self_attn.k_conv1d",
"model.layers.10.self_attn.k_proj",
"model.layers.10.self_attn.o_norm",
"model.layers.10.self_attn.o_proj",
"model.layers.10.self_attn.q_conv1d",
"model.layers.10.self_attn.q_proj",
"model.layers.10.self_attn.qkv_proj",
"model.layers.10.self_attn.v_conv1d",
"model.layers.10.self_attn.v_proj",
"model.layers.11.hc_attn_base",
"model.layers.11.hc_attn_fn",
"model.layers.11.hc_attn_scale",
"model.layers.11.hc_ffn_base",
"model.layers.11.hc_ffn_fn",
"model.layers.11.hc_ffn_scale",
"model.layers.11.input_layernorm",
"model.layers.11.mlp.gate",
"model.layers.11.mlp.gate.e_score_correction_bias",
"model.layers.11.post_attention_layernorm",
"model.layers.11.self_attn.indexer.index_kpool_compress_ape",
"model.layers.11.self_attn.indexer.index_kpool_compress_gate",
"model.layers.11.self_attn.indexer.k_norm",
"model.layers.11.self_attn.indexer.k_norm.bias",
"model.layers.11.self_attn.indexer.weights_proj",
"model.layers.11.self_attn.indexer.wk",
"model.layers.11.self_attn.indexer.wq_b",
"model.layers.11.self_attn.kv_a_layernorm",
"model.layers.11.self_attn.kv_b_proj",
"model.layers.11.self_attn.q_a_layernorm",
"model.layers.12.hc_attn_base",
"model.layers.12.hc_attn_fn",
"model.layers.12.hc_attn_scale",
"model.layers.12.hc_ffn_base",
"model.layers.12.hc_ffn_fn",
"model.layers.12.hc_ffn_scale",
"model.layers.12.input_layernorm",
"model.layers.12.mlp.gate",
"model.layers.12.mlp.gate.e_score_correction_bias",
"model.layers.12.post_attention_layernorm",
"model.layers.12.self_attn.A_log",
"model.layers.12.self_attn.b_proj",
"model.layers.12.self_attn.dt_bias",
"model.layers.12.self_attn.f_a_proj",
"model.layers.12.self_attn.f_b_proj",
"model.layers.12.self_attn.fused_qkvbfg_a_proj",
"model.layers.12.self_attn.g_a_proj",
"model.layers.12.self_attn.g_b_proj",
"model.layers.12.self_attn.k_conv1d",
"model.layers.12.self_attn.k_proj",
"model.layers.12.self_attn.o_norm",
"model.layers.12.self_attn.o_proj",
"model.layers.12.self_attn.q_conv1d",
"model.layers.12.self_attn.q_proj",
"model.layers.12.self_attn.qkv_proj",
"model.layers.12.self_attn.v_conv1d",
"model.layers.12.self_attn.v_proj",
"model.layers.13.hc_attn_base",
"model.layers.13.hc_attn_fn",
"model.layers.13.hc_attn_scale",
"model.layers.13.hc_ffn_base",
"model.layers.13.hc_ffn_fn",
"model.layers.13.hc_ffn_scale",
"model.layers.13.input_layernorm",
"model.layers.13.mlp.gate",
"model.layers.13.mlp.gate.e_score_correction_bias",
"model.layers.13.post_attention_layernorm",
"model.layers.13.self_attn.A_log",
"model.layers.13.self_attn.b_proj",
"model.layers.13.self_attn.dt_bias",
"model.layers.13.self_attn.f_a_proj",
"model.layers.13.self_attn.f_b_proj",
"model.layers.13.self_attn.fused_qkvbfg_a_proj",
"model.layers.13.self_attn.g_a_proj",
"model.layers.13.self_attn.g_b_proj",
"model.layers.13.self_attn.k_conv1d",
"model.layers.13.self_attn.k_proj",
"model.layers.13.self_attn.o_norm",
"model.layers.13.self_attn.o_proj",
"model.layers.13.self_attn.q_conv1d",
"model.layers.13.self_attn.q_proj",
"model.layers.13.self_attn.qkv_proj",
"model.layers.13.self_attn.v_conv1d",
"model.layers.13.self_attn.v_proj",
"model.layers.14.hc_attn_base",
"model.layers.14.hc_attn_fn",
"model.layers.14.hc_attn_scale",
"model.layers.14.hc_ffn_base",
"model.layers.14.hc_ffn_fn",
"model.layers.14.hc_ffn_scale",
"model.layers.14.input_layernorm",
"model.layers.14.mlp.gate",
"model.layers.14.mlp.gate.e_score_correction_bias",
"model.layers.14.post_attention_layernorm",
"model.layers.14.self_attn.A_log",
"model.layers.14.self_attn.b_proj",
"model.layers.14.self_attn.dt_bias",
"model.layers.14.self_attn.f_a_proj",
"model.layers.14.self_attn.f_b_proj",
"model.layers.14.self_attn.fused_qkvbfg_a_proj",
"model.layers.14.self_attn.g_a_proj",
"model.layers.14.self_attn.g_b_proj",
"model.layers.14.self_attn.k_conv1d",
"model.layers.14.self_attn.k_proj",
"model.layers.14.self_attn.o_norm",
"model.layers.14.self_attn.o_proj",
"model.layers.14.self_attn.q_conv1d",
"model.layers.14.self_attn.q_proj",
"model.layers.14.self_attn.qkv_proj",
"model.layers.14.self_attn.v_conv1d",
"model.layers.14.self_attn.v_proj",
"model.layers.15.hc_attn_base",
"model.layers.15.hc_attn_fn",
"model.layers.15.hc_attn_scale",
"model.layers.15.hc_ffn_base",
"model.layers.15.hc_ffn_fn",
"model.layers.15.hc_ffn_scale",
"model.layers.15.input_layernorm",
"model.layers.15.mlp.gate",
"model.layers.15.mlp.gate.e_score_correction_bias",
"model.layers.15.post_attention_layernorm",
"model.layers.15.self_attn.indexer.index_kpool_compress_ape",
"model.layers.15.self_attn.indexer.index_kpool_compress_gate",
"model.layers.15.self_attn.indexer.k_norm",
"model.layers.15.self_attn.indexer.k_norm.bias",
"model.layers.15.self_attn.indexer.weights_proj",
"model.layers.15.self_attn.indexer.wk",
"model.layers.15.self_attn.indexer.wq_b",
"model.layers.15.self_attn.kv_a_layernorm",
"model.layers.15.self_attn.kv_b_proj",
"model.layers.15.self_attn.q_a_layernorm",
"model.layers.16.hc_attn_base",
"model.layers.16.hc_attn_fn",
"model.layers.16.hc_attn_scale",
"model.layers.16.hc_ffn_base",
"model.layers.16.hc_ffn_fn",
"model.layers.16.hc_ffn_scale",
"model.layers.16.input_layernorm",
"model.layers.16.mlp.gate",
"model.layers.16.mlp.gate.e_score_correction_bias",
"model.layers.16.post_attention_layernorm",
"model.layers.16.self_attn.A_log",
"model.layers.16.self_attn.b_proj",
"model.layers.16.self_attn.dt_bias",
"model.layers.16.self_attn.f_a_proj",
"model.layers.16.self_attn.f_b_proj",
"model.layers.16.self_attn.fused_qkvbfg_a_proj",
"model.layers.16.self_attn.g_a_proj",
"model.layers.16.self_attn.g_b_proj",
"model.layers.16.self_attn.k_conv1d",
"model.layers.16.self_attn.k_proj",
"model.layers.16.self_attn.o_norm",
"model.layers.16.self_attn.o_proj",
"model.layers.16.self_attn.q_conv1d",
"model.layers.16.self_attn.q_proj",
"model.layers.16.self_attn.qkv_proj",
"model.layers.16.self_attn.v_conv1d",
"model.layers.16.self_attn.v_proj",
"model.layers.17.hc_attn_base",
"model.layers.17.hc_attn_fn",
"model.layers.17.hc_attn_scale",
"model.layers.17.hc_ffn_base",
"model.layers.17.hc_ffn_fn",
"model.layers.17.hc_ffn_scale",
"model.layers.17.input_layernorm",
"model.layers.17.mlp.gate",
"model.layers.17.mlp.gate.e_score_correction_bias",
"model.layers.17.post_attention_layernorm",
"model.layers.17.self_attn.A_log",
"model.layers.17.self_attn.b_proj",
"model.layers.17.self_attn.dt_bias",
"model.layers.17.self_attn.f_a_proj",
"model.layers.17.self_attn.f_b_proj",
"model.layers.17.self_attn.fused_qkvbfg_a_proj",
"model.layers.17.self_attn.g_a_proj",
"model.layers.17.self_attn.g_b_proj",
"model.layers.17.self_attn.k_conv1d",
"model.layers.17.self_attn.k_proj",
"model.layers.17.self_attn.o_norm",
"model.layers.17.self_attn.o_proj",
"model.layers.17.self_attn.q_conv1d",
"model.layers.17.self_attn.q_proj",
"model.layers.17.self_attn.qkv_proj",
"model.layers.17.self_attn.v_conv1d",
"model.layers.17.self_attn.v_proj",
"model.layers.18.hc_attn_base",
"model.layers.18.hc_attn_fn",
"model.layers.18.hc_attn_scale",
"model.layers.18.hc_ffn_base",
"model.layers.18.hc_ffn_fn",
"model.layers.18.hc_ffn_scale",
"model.layers.18.input_layernorm",
"model.layers.18.mlp.gate",
"model.layers.18.mlp.gate.e_score_correction_bias",
"model.layers.18.post_attention_layernorm",
"model.layers.18.self_attn.A_log",
"model.layers.18.self_attn.b_proj",
"model.layers.18.self_attn.dt_bias",
"model.layers.18.self_attn.f_a_proj",
"model.layers.18.self_attn.f_b_proj",
"model.layers.18.self_attn.fused_qkvbfg_a_proj",
"model.layers.18.self_attn.g_a_proj",
"model.layers.18.self_attn.g_b_proj",
"model.layers.18.self_attn.k_conv1d",
"model.layers.18.self_attn.k_proj",
"model.layers.18.self_attn.o_norm",
"model.layers.18.self_attn.o_proj",
"model.layers.18.self_attn.q_conv1d",
"model.layers.18.self_attn.q_proj",
"model.layers.18.self_attn.qkv_proj",
"model.layers.18.self_attn.v_conv1d",
"model.layers.18.self_attn.v_proj",
"model.layers.19.hc_attn_base",
"model.layers.19.hc_attn_fn",
"model.layers.19.hc_attn_scale",
"model.layers.19.hc_ffn_base",
"model.layers.19.hc_ffn_fn",
"model.layers.19.hc_ffn_scale",
"model.layers.19.input_layernorm",
"model.layers.19.mlp.gate",
"model.layers.19.mlp.gate.e_score_correction_bias",
"model.layers.19.post_attention_layernorm",
"model.layers.19.self_attn.indexer.index_kpool_compress_ape",
"model.layers.19.self_attn.indexer.index_kpool_compress_gate",
"model.layers.19.self_attn.indexer.k_norm",
"model.layers.19.self_attn.indexer.k_norm.bias",
"model.layers.19.self_attn.indexer.weights_proj",
"model.layers.19.self_attn.indexer.wk",
"model.layers.19.self_attn.indexer.wq_b",
"model.layers.19.self_attn.kv_a_layernorm",
"model.layers.19.self_attn.kv_b_proj",
"model.layers.19.self_attn.q_a_layernorm",
"model.layers.2.hc_attn_base",
"model.layers.2.hc_attn_fn",
"model.layers.2.hc_attn_scale",
"model.layers.2.hc_ffn_base",
"model.layers.2.hc_ffn_fn",
"model.layers.2.hc_ffn_scale",
"model.layers.2.input_layernorm",
"model.layers.2.post_attention_layernorm",
"model.layers.2.self_attn.A_log",
"model.layers.2.self_attn.b_proj",
"model.layers.2.self_attn.dt_bias",
"model.layers.2.self_attn.f_a_proj",
"model.layers.2.self_attn.f_b_proj",
"model.layers.2.self_attn.fused_qkvbfg_a_proj",
"model.layers.2.self_attn.g_a_proj",
"model.layers.2.self_attn.g_b_proj",
"model.layers.2.self_attn.k_conv1d",
"model.layers.2.self_attn.k_proj",
"model.layers.2.self_attn.o_norm",
"model.layers.2.self_attn.o_proj",
"model.layers.2.self_attn.q_conv1d",
"model.layers.2.self_attn.q_proj",
"model.layers.2.self_attn.qkv_proj",
"model.layers.2.self_attn.v_conv1d",
"model.layers.2.self_attn.v_proj",
"model.layers.20.hc_attn_base",
"model.layers.20.hc_attn_fn",
"model.layers.20.hc_attn_scale",
"model.layers.20.hc_ffn_base",
"model.layers.20.hc_ffn_fn",
"model.layers.20.hc_ffn_scale",
"model.layers.20.input_layernorm",
"model.layers.20.mlp.gate",
"model.layers.20.mlp.gate.e_score_correction_bias",
"model.layers.20.post_attention_layernorm",
"model.layers.20.self_attn.A_log",
"model.layers.20.self_attn.b_proj",
"model.layers.20.self_attn.dt_bias",
"model.layers.20.self_attn.f_a_proj",
"model.layers.20.self_attn.f_b_proj",
"model.layers.20.self_attn.fused_qkvbfg_a_proj",
"model.layers.20.self_attn.g_a_proj",
"model.layers.20.self_attn.g_b_proj",
"model.layers.20.self_attn.k_conv1d",
"model.layers.20.self_attn.k_proj",
"model.layers.20.self_attn.o_norm",
"model.layers.20.self_attn.o_proj",
"model.layers.20.self_attn.q_conv1d",
"model.layers.20.self_attn.q_proj",
"model.layers.20.self_attn.qkv_proj",
"model.layers.20.self_attn.v_conv1d",
"model.layers.20.self_attn.v_proj",
"model.layers.21.hc_attn_base",
"model.layers.21.hc_attn_fn",
"model.layers.21.hc_attn_scale",
"model.layers.21.hc_ffn_base",
"model.layers.21.hc_ffn_fn",
"model.layers.21.hc_ffn_scale",
"model.layers.21.input_layernorm",
"model.layers.21.mlp.gate",
"model.layers.21.mlp.gate.e_score_correction_bias",
"model.layers.21.post_attention_layernorm",
"model.layers.21.self_attn.A_log",
"model.layers.21.self_attn.b_proj",
"model.layers.21.self_attn.dt_bias",
"model.layers.21.self_attn.f_a_proj",
"model.layers.21.self_attn.f_b_proj",
"model.layers.21.self_attn.fused_qkvbfg_a_proj",
"model.layers.21.self_attn.g_a_proj",
"model.layers.21.self_attn.g_b_proj",
"model.layers.21.self_attn.k_conv1d",
"model.layers.21.self_attn.k_proj",
"model.layers.21.self_attn.o_norm",
"model.layers.21.self_attn.o_proj",
"model.layers.21.self_attn.q_conv1d",
"model.layers.21.self_attn.q_proj",
"model.layers.21.self_attn.qkv_proj",
"model.layers.21.self_attn.v_conv1d",
"model.layers.21.self_attn.v_proj",
"model.layers.22.hc_attn_base",
"model.layers.22.hc_attn_fn",
"model.layers.22.hc_attn_scale",
"model.layers.22.hc_ffn_base",
"model.layers.22.hc_ffn_fn",
"model.layers.22.hc_ffn_scale",
"model.layers.22.input_layernorm",
"model.layers.22.mlp.gate",
"model.layers.22.mlp.gate.e_score_correction_bias",
"model.layers.22.post_attention_layernorm",
"model.layers.22.self_attn.A_log",
"model.layers.22.self_attn.b_proj",
"model.layers.22.self_attn.dt_bias",
"model.layers.22.self_attn.f_a_proj",
"model.layers.22.self_attn.f_b_proj",
"model.layers.22.self_attn.fused_qkvbfg_a_proj",
"model.layers.22.self_attn.g_a_proj",
"model.layers.22.self_attn.g_b_proj",
"model.layers.22.self_attn.k_conv1d",
"model.layers.22.self_attn.k_proj",
"model.layers.22.self_attn.o_norm",
"model.layers.22.self_attn.o_proj",
"model.layers.22.self_attn.q_conv1d",
"model.layers.22.self_attn.q_proj",
"model.layers.22.self_attn.qkv_proj",
"model.layers.22.self_attn.v_conv1d",
"model.layers.22.self_attn.v_proj",
"model.layers.23.hc_attn_base",
"model.layers.23.hc_attn_fn",
"model.layers.23.hc_attn_scale",
"model.layers.23.hc_ffn_base",
"model.layers.23.hc_ffn_fn",
"model.layers.23.hc_ffn_scale",
"model.layers.23.input_layernorm",
"model.layers.23.mlp.gate",
"model.layers.23.mlp.gate.e_score_correction_bias",
"model.layers.23.post_attention_layernorm",
"model.layers.23.self_attn.indexer.index_kpool_compress_ape",
"model.layers.23.self_attn.indexer.index_kpool_compress_gate",
"model.layers.23.self_attn.indexer.k_norm",
"model.layers.23.self_attn.indexer.k_norm.bias",
"model.layers.23.self_attn.indexer.weights_proj",
"model.layers.23.self_attn.indexer.wk",
"model.layers.23.self_attn.indexer.wq_b",
"model.layers.23.self_attn.kv_a_layernorm",
"model.layers.23.self_attn.kv_b_proj",
"model.layers.23.self_attn.q_a_layernorm",
"model.layers.24.hc_attn_base",
"model.layers.24.hc_attn_fn",
"model.layers.24.hc_attn_scale",
"model.layers.24.hc_ffn_base",
"model.layers.24.hc_ffn_fn",
"model.layers.24.hc_ffn_scale",
"model.layers.24.input_layernorm",
"model.layers.24.mlp.gate",
"model.layers.24.mlp.gate.e_score_correction_bias",
"model.layers.24.post_attention_layernorm",
"model.layers.24.self_attn.A_log",
"model.layers.24.self_attn.b_proj",
"model.layers.24.self_attn.dt_bias",
"model.layers.24.self_attn.f_a_proj",
"model.layers.24.self_attn.f_b_proj",
"model.layers.24.self_attn.fused_qkvbfg_a_proj",
"model.layers.24.self_attn.g_a_proj",
"model.layers.24.self_attn.g_b_proj",
"model.layers.24.self_attn.k_conv1d",
"model.layers.24.self_attn.k_proj",
"model.layers.24.self_attn.o_norm",
"model.layers.24.self_attn.o_proj",
"model.layers.24.self_attn.q_conv1d",
"model.layers.24.self_attn.q_proj",
"model.layers.24.self_attn.qkv_proj",
"model.layers.24.self_attn.v_conv1d",
"model.layers.24.self_attn.v_proj",
"model.layers.25.hc_attn_base",
"model.layers.25.hc_attn_fn",
"model.layers.25.hc_attn_scale",
"model.layers.25.hc_ffn_base",
"model.layers.25.hc_ffn_fn",
"model.layers.25.hc_ffn_scale",
"model.layers.25.input_layernorm",
"model.layers.25.mlp.gate",
"model.layers.25.mlp.gate.e_score_correction_bias",
"model.layers.25.post_attention_layernorm",
"model.layers.25.self_attn.A_log",
"model.layers.25.self_attn.b_proj",
"model.layers.25.self_attn.dt_bias",
"model.layers.25.self_attn.f_a_proj",
"model.layers.25.self_attn.f_b_proj",
"model.layers.25.self_attn.fused_qkvbfg_a_proj",
"model.layers.25.self_attn.g_a_proj",
"model.layers.25.self_attn.g_b_proj",
"model.layers.25.self_attn.k_conv1d",
"model.layers.25.self_attn.k_proj",
"model.layers.25.self_attn.o_norm",
"model.layers.25.self_attn.o_proj",
"model.layers.25.self_attn.q_conv1d",
"model.layers.25.self_attn.q_proj",
"model.layers.25.self_attn.qkv_proj",
"model.layers.25.self_attn.v_conv1d",
"model.layers.25.self_attn.v_proj",
"model.layers.26.hc_attn_base",
"model.layers.26.hc_attn_fn",
"model.layers.26.hc_attn_scale",
"model.layers.26.hc_ffn_base",
"model.layers.26.hc_ffn_fn",
"model.layers.26.hc_ffn_scale",
"model.layers.26.input_layernorm",
"model.layers.26.mlp.gate",
"model.layers.26.mlp.gate.e_score_correction_bias",
"model.layers.26.post_attention_layernorm",
"model.layers.26.self_attn.A_log",
"model.layers.26.self_attn.b_proj",
"model.layers.26.self_attn.dt_bias",
"model.layers.26.self_attn.f_a_proj",
"model.layers.26.self_attn.f_b_proj",
"model.layers.26.self_attn.fused_qkvbfg_a_proj",
"model.layers.26.self_attn.g_a_proj",
"model.layers.26.self_attn.g_b_proj",
"model.layers.26.self_attn.k_conv1d",
"model.layers.26.self_attn.k_proj",
"model.layers.26.self_attn.o_norm",
"model.layers.26.self_attn.o_proj",
"model.layers.26.self_attn.q_conv1d",
"model.layers.26.self_attn.q_proj",
"model.layers.26.self_attn.qkv_proj",
"model.layers.26.self_attn.v_conv1d",
"model.layers.26.self_attn.v_proj",
"model.layers.27.hc_attn_base",
"model.layers.27.hc_attn_fn",
"model.layers.27.hc_attn_scale",
"model.layers.27.hc_ffn_base",
"model.layers.27.hc_ffn_fn",
"model.layers.27.hc_ffn_scale",
"model.layers.27.input_layernorm",
"model.layers.27.mlp.gate",
"model.layers.27.mlp.gate.e_score_correction_bias",
"model.layers.27.post_attention_layernorm",
"model.layers.27.self_attn.indexer.index_kpool_compress_ape",
"model.layers.27.self_attn.indexer.index_kpool_compress_gate",
"model.layers.27.self_attn.indexer.k_norm",
"model.layers.27.self_attn.indexer.k_norm.bias",
"model.layers.27.self_attn.indexer.weights_proj",
"model.layers.27.self_attn.indexer.wk",
"model.layers.27.self_attn.indexer.wq_b",
"model.layers.27.self_attn.kv_a_layernorm",
"model.layers.27.self_attn.kv_b_proj",
"model.layers.27.self_attn.q_a_layernorm",
"model.layers.28.hc_attn_base",
"model.layers.28.hc_attn_fn",
"model.layers.28.hc_attn_scale",
"model.layers.28.hc_ffn_base",
"model.layers.28.hc_ffn_fn",
"model.layers.28.hc_ffn_scale",
"model.layers.28.input_layernorm",
"model.layers.28.mlp.gate",
"model.layers.28.mlp.gate.e_score_correction_bias",
"model.layers.28.post_attention_layernorm",
"model.layers.28.self_attn.A_log",
"model.layers.28.self_attn.b_proj",
"model.layers.28.self_attn.dt_bias",
"model.layers.28.self_attn.f_a_proj",
"model.layers.28.self_attn.f_b_proj",
"model.layers.28.self_attn.fused_qkvbfg_a_proj",
"model.layers.28.self_attn.g_a_proj",
"model.layers.28.self_attn.g_b_proj",
"model.layers.28.self_attn.k_conv1d",
"model.layers.28.self_attn.k_proj",
"model.layers.28.self_attn.o_norm",
"model.layers.28.self_attn.o_proj",
"model.layers.28.self_attn.q_conv1d",
"model.layers.28.self_attn.q_proj",
"model.layers.28.self_attn.qkv_proj",
"model.layers.28.self_attn.v_conv1d",
"model.layers.28.self_attn.v_proj",
"model.layers.29.hc_attn_base",
"model.layers.29.hc_attn_fn",
"model.layers.29.hc_attn_scale",
"model.layers.29.hc_ffn_base",
"model.layers.29.hc_ffn_fn",
"model.layers.29.hc_ffn_scale",
"model.layers.29.input_layernorm",
"model.layers.29.mlp.gate",
"model.layers.29.mlp.gate.e_score_correction_bias",
"model.layers.29.post_attention_layernorm",
"model.layers.29.self_attn.A_log",
"model.layers.29.self_attn.b_proj",
"model.layers.29.self_attn.dt_bias",
"model.layers.29.self_attn.f_a_proj",
"model.layers.29.self_attn.f_b_proj",
"model.layers.29.self_attn.fused_qkvbfg_a_proj",
"model.layers.29.self_attn.g_a_proj",
"model.layers.29.self_attn.g_b_proj",
"model.layers.29.self_attn.k_conv1d",
"model.layers.29.self_attn.k_proj",
"model.layers.29.self_attn.o_norm",
"model.layers.29.self_attn.o_proj",
"model.layers.29.self_attn.q_conv1d",
"model.layers.29.self_attn.q_proj",
"model.layers.29.self_attn.qkv_proj",
"model.layers.29.self_attn.v_conv1d",
"model.layers.29.self_attn.v_proj",
"model.layers.3.hc_attn_base",
"model.layers.3.hc_attn_fn",
"model.layers.3.hc_attn_scale",
"model.layers.3.hc_ffn_base",
"model.layers.3.hc_ffn_fn",
"model.layers.3.hc_ffn_scale",
"model.layers.3.input_layernorm",
"model.layers.3.mlp.gate",
"model.layers.3.mlp.gate.e_score_correction_bias",
"model.layers.3.post_attention_layernorm",
"model.layers.3.self_attn.indexer.index_kpool_compress_ape",
"model.layers.3.self_attn.indexer.index_kpool_compress_gate",
"model.layers.3.self_attn.indexer.k_norm",
"model.layers.3.self_attn.indexer.k_norm.bias",
"model.layers.3.self_attn.indexer.weights_proj",
"model.layers.3.self_attn.indexer.wk",
"model.layers.3.self_attn.indexer.wq_b",
"model.layers.3.self_attn.kv_a_layernorm",
"model.layers.3.self_attn.kv_b_proj",
"model.layers.3.self_attn.q_a_layernorm",
"model.layers.30.hc_attn_base",
"model.layers.30.hc_attn_fn",
"model.layers.30.hc_attn_scale",
"model.layers.30.hc_ffn_base",
"model.layers.30.hc_ffn_fn",
"model.layers.30.hc_ffn_scale",
"model.layers.30.input_layernorm",
"model.layers.30.mlp.gate",
"model.layers.30.mlp.gate.e_score_correction_bias",
"model.layers.30.post_attention_layernorm",
"model.layers.30.self_attn.A_log",
"model.layers.30.self_attn.b_proj",
"model.layers.30.self_attn.dt_bias",
"model.layers.30.self_attn.f_a_proj",
"model.layers.30.self_attn.f_b_proj",
"model.layers.30.self_attn.fused_qkvbfg_a_proj",
"model.layers.30.self_attn.g_a_proj",
"model.layers.30.self_attn.g_b_proj",
"model.layers.30.self_attn.k_conv1d",
"model.layers.30.self_attn.k_proj",
"model.layers.30.self_attn.o_norm",
"model.layers.30.self_attn.o_proj",
"model.layers.30.self_attn.q_conv1d",
"model.layers.30.self_attn.q_proj",
"model.layers.30.self_attn.qkv_proj",
"model.layers.30.self_attn.v_conv1d",
"model.layers.30.self_attn.v_proj",
"model.layers.31.hc_attn_base",
"model.layers.31.hc_attn_fn",
"model.layers.31.hc_attn_scale",
"model.layers.31.hc_ffn_base",
"model.layers.31.hc_ffn_fn",
"model.layers.31.hc_ffn_scale",
"model.layers.31.input_layernorm",
"model.layers.31.mlp.gate",
"model.layers.31.mlp.gate.e_score_correction_bias",
"model.layers.31.post_attention_layernorm",
"model.layers.31.self_attn.indexer.index_kpool_compress_ape",
"model.layers.31.self_attn.indexer.index_kpool_compress_gate",
"model.layers.31.self_attn.indexer.k_norm",
"model.layers.31.self_attn.indexer.k_norm.bias",
"model.layers.31.self_attn.indexer.weights_proj",
"model.layers.31.self_attn.indexer.wk",
"model.layers.31.self_attn.indexer.wq_b",
"model.layers.31.self_attn.kv_a_layernorm",
"model.layers.31.self_attn.kv_b_proj",
"model.layers.31.self_attn.q_a_layernorm",
"model.layers.32.hc_attn_base",
"model.layers.32.hc_attn_fn",
"model.layers.32.hc_attn_scale",
"model.layers.32.hc_ffn_base",
"model.layers.32.hc_ffn_fn",
"model.layers.32.hc_ffn_scale",
"model.layers.32.input_layernorm",
"model.layers.32.mlp.gate",
"model.layers.32.mlp.gate.e_score_correction_bias",
"model.layers.32.post_attention_layernorm",
"model.layers.32.self_attn.A_log",
"model.layers.32.self_attn.b_proj",
"model.layers.32.self_attn.dt_bias",
"model.layers.32.self_attn.f_a_proj",
"model.layers.32.self_attn.f_b_proj",
"model.layers.32.self_attn.fused_qkvbfg_a_proj",
"model.layers.32.self_attn.g_a_proj",
"model.layers.32.self_attn.g_b_proj",
"model.layers.32.self_attn.k_conv1d",
"model.layers.32.self_attn.k_proj",
"model.layers.32.self_attn.o_norm",
"model.layers.32.self_attn.o_proj",
"model.layers.32.self_attn.q_conv1d",
"model.layers.32.self_attn.q_proj",
"model.layers.32.self_attn.qkv_proj",
"model.layers.32.self_attn.v_conv1d",
"model.layers.32.self_attn.v_proj",
"model.layers.33.hc_attn_base",
"model.layers.33.hc_attn_fn",
"model.layers.33.hc_attn_scale",
"model.layers.33.hc_ffn_base",
"model.layers.33.hc_ffn_fn",
"model.layers.33.hc_ffn_scale",
"model.layers.33.input_layernorm",
"model.layers.33.mlp.gate",
"model.layers.33.mlp.gate.e_score_correction_bias",
"model.layers.33.post_attention_layernorm",
"model.layers.33.self_attn.A_log",
"model.layers.33.self_attn.b_proj",
"model.layers.33.self_attn.dt_bias",
"model.layers.33.self_attn.f_a_proj",
"model.layers.33.self_attn.f_b_proj",
"model.layers.33.self_attn.fused_qkvbfg_a_proj",
"model.layers.33.self_attn.g_a_proj",
"model.layers.33.self_attn.g_b_proj",
"model.layers.33.self_attn.k_conv1d",
"model.layers.33.self_attn.k_proj",
"model.layers.33.self_attn.o_norm",
"model.layers.33.self_attn.o_proj",
"model.layers.33.self_attn.q_conv1d",
"model.layers.33.self_attn.q_proj",
"model.layers.33.self_attn.qkv_proj",
"model.layers.33.self_attn.v_conv1d",
"model.layers.33.self_attn.v_proj",
"model.layers.34.hc_attn_base",
"model.layers.34.hc_attn_fn",
"model.layers.34.hc_attn_scale",
"model.layers.34.hc_ffn_base",
"model.layers.34.hc_ffn_fn",
"model.layers.34.hc_ffn_scale",
"model.layers.34.input_layernorm",
"model.layers.34.mlp.gate",
"model.layers.34.mlp.gate.e_score_correction_bias",
"model.layers.34.post_attention_layernorm",
"model.layers.34.self_attn.A_log",
"model.layers.34.self_attn.b_proj",
"model.layers.34.self_attn.dt_bias",
"model.layers.34.self_attn.f_a_proj",
"model.layers.34.self_attn.f_b_proj",
"model.layers.34.self_attn.fused_qkvbfg_a_proj",
"model.layers.34.self_attn.g_a_proj",
"model.layers.34.self_attn.g_b_proj",
"model.layers.34.self_attn.k_conv1d",
"model.layers.34.self_attn.k_proj",
"model.layers.34.self_attn.o_norm",
"model.layers.34.self_attn.o_proj",
"model.layers.34.self_attn.q_conv1d",
"model.layers.34.self_attn.q_proj",
"model.layers.34.self_attn.qkv_proj",
"model.layers.34.self_attn.v_conv1d",
"model.layers.34.self_attn.v_proj",
"model.layers.35.hc_attn_base",
"model.layers.35.hc_attn_fn",
"model.layers.35.hc_attn_scale",
"model.layers.35.hc_ffn_base",
"model.layers.35.hc_ffn_fn",
"model.layers.35.hc_ffn_scale",
"model.layers.35.input_layernorm",
"model.layers.35.mlp.gate",
"model.layers.35.mlp.gate.e_score_correction_bias",
"model.layers.35.post_attention_layernorm",
"model.layers.35.self_attn.indexer.index_kpool_compress_ape",
"model.layers.35.self_attn.indexer.index_kpool_compress_gate",
"model.layers.35.self_attn.indexer.k_norm",
"model.layers.35.self_attn.indexer.k_norm.bias",
"model.layers.35.self_attn.indexer.weights_proj",
"model.layers.35.self_attn.indexer.wk",
"model.layers.35.self_attn.indexer.wq_b",
"model.layers.35.self_attn.kv_a_layernorm",
"model.layers.35.self_attn.kv_b_proj",
"model.layers.35.self_attn.q_a_layernorm",
"model.layers.36.hc_attn_base",
"model.layers.36.hc_attn_fn",
"model.layers.36.hc_attn_scale",
"model.layers.36.hc_ffn_base",
"model.layers.36.hc_ffn_fn",
"model.layers.36.hc_ffn_scale",
"model.layers.36.input_layernorm",
"model.layers.36.mlp.gate",
"model.layers.36.mlp.gate.e_score_correction_bias",
"model.layers.36.post_attention_layernorm",
"model.layers.36.self_attn.A_log",
"model.layers.36.self_attn.b_proj",
"model.layers.36.self_attn.dt_bias",
"model.layers.36.self_attn.f_a_proj",
"model.layers.36.self_attn.f_b_proj",
"model.layers.36.self_attn.fused_qkvbfg_a_proj",
"model.layers.36.self_attn.g_a_proj",
"model.layers.36.self_attn.g_b_proj",
"model.layers.36.self_attn.k_conv1d",
"model.layers.36.self_attn.k_proj",
"model.layers.36.self_attn.o_norm",
"model.layers.36.self_attn.o_proj",
"model.layers.36.self_attn.q_conv1d",
"model.layers.36.self_attn.q_proj",
"model.layers.36.self_attn.qkv_proj",
"model.layers.36.self_attn.v_conv1d",
"model.layers.36.self_attn.v_proj",
"model.layers.37.hc_attn_base",
"model.layers.37.hc_attn_fn",
"model.layers.37.hc_attn_scale",
"model.layers.37.hc_ffn_base",
"model.layers.37.hc_ffn_fn",
"model.layers.37.hc_ffn_scale",
"model.layers.37.input_layernorm",
"model.layers.37.mlp.gate",
"model.layers.37.mlp.gate.e_score_correction_bias",
"model.layers.37.post_attention_layernorm",
"model.layers.37.self_attn.A_log",
"model.layers.37.self_attn.b_proj",
"model.layers.37.self_attn.dt_bias",
"model.layers.37.self_attn.f_a_proj",
"model.layers.37.self_attn.f_b_proj",
"model.layers.37.self_attn.fused_qkvbfg_a_proj",
"model.layers.37.self_attn.g_a_proj",
"model.layers.37.self_attn.g_b_proj",
"model.layers.37.self_attn.k_conv1d",
"model.layers.37.self_attn.k_proj",
"model.layers.37.self_attn.o_norm",
"model.layers.37.self_attn.o_proj",
"model.layers.37.self_attn.q_conv1d",
"model.layers.37.self_attn.q_proj",
"model.layers.37.self_attn.qkv_proj",
"model.layers.37.self_attn.v_conv1d",
"model.layers.37.self_attn.v_proj",
"model.layers.38.hc_attn_base",
"model.layers.38.hc_attn_fn",
"model.layers.38.hc_attn_scale",
"model.layers.38.hc_ffn_base",
"model.layers.38.hc_ffn_fn",
"model.layers.38.hc_ffn_scale",
"model.layers.38.input_layernorm",
"model.layers.38.mlp.gate",
"model.layers.38.mlp.gate.e_score_correction_bias",
"model.layers.38.post_attention_layernorm",
"model.layers.38.self_attn.A_log",
"model.layers.38.self_attn.b_proj",
"model.layers.38.self_attn.dt_bias",
"model.layers.38.self_attn.f_a_proj",
"model.layers.38.self_attn.f_b_proj",
"model.layers.38.self_attn.fused_qkvbfg_a_proj",
"model.layers.38.self_attn.g_a_proj",
"model.layers.38.self_attn.g_b_proj",
"model.layers.38.self_attn.k_conv1d",
"model.layers.38.self_attn.k_proj",
"model.layers.38.self_attn.o_norm",
"model.layers.38.self_attn.o_proj",
"model.layers.38.self_attn.q_conv1d",
"model.layers.38.self_attn.q_proj",
"model.layers.38.self_attn.qkv_proj",
"model.layers.38.self_attn.v_conv1d",
"model.layers.38.self_attn.v_proj",
"model.layers.39.hc_attn_base",
"model.layers.39.hc_attn_fn",
"model.layers.39.hc_attn_scale",
"model.layers.39.hc_ffn_base",
"model.layers.39.hc_ffn_fn",
"model.layers.39.hc_ffn_scale",
"model.layers.39.input_layernorm",
"model.layers.39.mlp.gate",
"model.layers.39.mlp.gate.e_score_correction_bias",
"model.layers.39.post_attention_layernorm",
"model.layers.39.self_attn.indexer.index_kpool_compress_ape",
"model.layers.39.self_attn.indexer.index_kpool_compress_gate",
"model.layers.39.self_attn.indexer.k_norm",
"model.layers.39.self_attn.indexer.k_norm.bias",
"model.layers.39.self_attn.indexer.weights_proj",
"model.layers.39.self_attn.indexer.wk",
"model.layers.39.self_attn.indexer.wq_b",
"model.layers.39.self_attn.kv_a_layernorm",
"model.layers.39.self_attn.kv_b_proj",
"model.layers.39.self_attn.q_a_layernorm",
"model.layers.4.hc_attn_base",
"model.layers.4.hc_attn_fn",
"model.layers.4.hc_attn_scale",
"model.layers.4.hc_ffn_base",
"model.layers.4.hc_ffn_fn",
"model.layers.4.hc_ffn_scale",
"model.layers.4.input_layernorm",
"model.layers.4.mlp.gate",
"model.layers.4.mlp.gate.e_score_correction_bias",
"model.layers.4.post_attention_layernorm",
"model.layers.4.self_attn.A_log",
"model.layers.4.self_attn.b_proj",
"model.layers.4.self_attn.dt_bias",
"model.layers.4.self_attn.f_a_proj",
"model.layers.4.self_attn.f_b_proj",
"model.layers.4.self_attn.fused_qkvbfg_a_proj",
"model.layers.4.self_attn.g_a_proj",
"model.layers.4.self_attn.g_b_proj",
"model.layers.4.self_attn.k_conv1d",
"model.layers.4.self_attn.k_proj",
"model.layers.4.self_attn.o_norm",
"model.layers.4.self_attn.o_proj",
"model.layers.4.self_attn.q_conv1d",
"model.layers.4.self_attn.q_proj",
"model.layers.4.self_attn.qkv_proj",
"model.layers.4.self_attn.v_conv1d",
"model.layers.4.self_attn.v_proj",
"model.layers.40.hc_attn_base",
"model.layers.40.hc_attn_fn",
"model.layers.40.hc_attn_scale",
"model.layers.40.hc_ffn_base",
"model.layers.40.hc_ffn_fn",
"model.layers.40.hc_ffn_scale",
"model.layers.40.input_layernorm",
"model.layers.40.mlp.gate",
"model.layers.40.mlp.gate.e_score_correction_bias",
"model.layers.40.post_attention_layernorm",
"model.layers.40.self_attn.A_log",
"model.layers.40.self_attn.b_proj",
"model.layers.40.self_attn.dt_bias",
"model.layers.40.self_attn.f_a_proj",
"model.layers.40.self_attn.f_b_proj",
"model.layers.40.self_attn.fused_qkvbfg_a_proj",
"model.layers.40.self_attn.g_a_proj",
"model.layers.40.self_attn.g_b_proj",
"model.layers.40.self_attn.k_conv1d",
"model.layers.40.self_attn.k_proj",
"model.layers.40.self_attn.o_norm",
"model.layers.40.self_attn.o_proj",
"model.layers.40.self_attn.q_conv1d",
"model.layers.40.self_attn.q_proj",
"model.layers.40.self_attn.qkv_proj",
"model.layers.40.self_attn.v_conv1d",
"model.layers.40.self_attn.v_proj",
"model.layers.41.hc_attn_base",
"model.layers.41.hc_attn_fn",
"model.layers.41.hc_attn_scale",
"model.layers.41.hc_ffn_base",
"model.layers.41.hc_ffn_fn",
"model.layers.41.hc_ffn_scale",
"model.layers.41.input_layernorm",
"model.layers.41.mlp.gate",
"model.layers.41.mlp.gate.e_score_correction_bias",
"model.layers.41.post_attention_layernorm",
"model.layers.41.self_attn.A_log",
"model.layers.41.self_attn.b_proj",
"model.layers.41.self_attn.dt_bias",
"model.layers.41.self_attn.f_a_proj",
"model.layers.41.self_attn.f_b_proj",
"model.layers.41.self_attn.fused_qkvbfg_a_proj",
"model.layers.41.self_attn.g_a_proj",
"model.layers.41.self_attn.g_b_proj",
"model.layers.41.self_attn.k_conv1d",
"model.layers.41.self_attn.k_proj",
"model.layers.41.self_attn.o_norm",
"model.layers.41.self_attn.o_proj",
"model.layers.41.self_attn.q_conv1d",
"model.layers.41.self_attn.q_proj",
"model.layers.41.self_attn.qkv_proj",
"model.layers.41.self_attn.v_conv1d",
"model.layers.41.self_attn.v_proj",
"model.layers.42.hc_attn_base",
"model.layers.42.hc_attn_fn",
"model.layers.42.hc_attn_scale",
"model.layers.42.hc_ffn_base",
"model.layers.42.hc_ffn_fn",
"model.layers.42.hc_ffn_scale",
"model.layers.42.input_layernorm",
"model.layers.42.mlp.gate",
"model.layers.42.mlp.gate.e_score_correction_bias",
"model.layers.42.post_attention_layernorm",
"model.layers.42.self_attn.A_log",
"model.layers.42.self_attn.b_proj",
"model.layers.42.self_attn.dt_bias",
"model.layers.42.self_attn.f_a_proj",
"model.layers.42.self_attn.f_b_proj",
"model.layers.42.self_attn.fused_qkvbfg_a_proj",
"model.layers.42.self_attn.g_a_proj",
"model.layers.42.self_attn.g_b_proj",
"model.layers.42.self_attn.k_conv1d",
"model.layers.42.self_attn.k_proj",
"model.layers.42.self_attn.o_norm",
"model.layers.42.self_attn.o_proj",
"model.layers.42.self_attn.q_conv1d",
"model.layers.42.self_attn.q_proj",
"model.layers.42.self_attn.qkv_proj",
"model.layers.42.self_attn.v_conv1d",
"model.layers.42.self_attn.v_proj",
"model.layers.43.hc_attn_base",
"model.layers.43.hc_attn_fn",
"model.layers.43.hc_attn_scale",
"model.layers.43.hc_ffn_base",
"model.layers.43.hc_ffn_fn",
"model.layers.43.hc_ffn_scale",
"model.layers.43.input_layernorm",
"model.layers.43.mlp.gate",
"model.layers.43.mlp.gate.e_score_correction_bias",
"model.layers.43.post_attention_layernorm",
"model.layers.43.self_attn.indexer.index_kpool_compress_ape",
"model.layers.43.self_attn.indexer.index_kpool_compress_gate",
"model.layers.43.self_attn.indexer.k_norm",
"model.layers.43.self_attn.indexer.k_norm.bias",
"model.layers.43.self_attn.indexer.weights_proj",
"model.layers.43.self_attn.indexer.wk",
"model.layers.43.self_attn.indexer.wq_b",
"model.layers.43.self_attn.kv_a_layernorm",
"model.layers.43.self_attn.kv_b_proj",
"model.layers.43.self_attn.q_a_layernorm",
"model.layers.44.hc_attn_base",
"model.layers.44.hc_attn_fn",
"model.layers.44.hc_attn_scale",
"model.layers.44.hc_ffn_base",
"model.layers.44.hc_ffn_fn",
"model.layers.44.hc_ffn_scale",
"model.layers.44.input_layernorm",
"model.layers.44.mlp.gate",
"model.layers.44.mlp.gate.e_score_correction_bias",
"model.layers.44.post_attention_layernorm",
"model.layers.44.self_attn.A_log",
"model.layers.44.self_attn.b_proj",
"model.layers.44.self_attn.dt_bias",
"model.layers.44.self_attn.f_a_proj",
"model.layers.44.self_attn.f_b_proj",
"model.layers.44.self_attn.fused_qkvbfg_a_proj",
"model.layers.44.self_attn.g_a_proj",
"model.layers.44.self_attn.g_b_proj",
"model.layers.44.self_attn.k_conv1d",
"model.layers.44.self_attn.k_proj",
"model.layers.44.self_attn.o_norm",
"model.layers.44.self_attn.o_proj",
"model.layers.44.self_attn.q_conv1d",
"model.layers.44.self_attn.q_proj",
"model.layers.44.self_attn.qkv_proj",
"model.layers.44.self_attn.v_conv1d",
"model.layers.44.self_attn.v_proj",
"model.layers.45.eh_proj",
"model.layers.45.enorm",
"model.layers.45.hnorm",
"model.layers.45.input_layernorm",
"model.layers.45.mlp.gate",
"model.layers.45.mlp.gate.e_score_correction_bias",
"model.layers.45.post_attention_layernorm",
"model.layers.45.self_attn.indexer.index_kpool_compress_ape",
"model.layers.45.self_attn.indexer.index_kpool_compress_gate",
"model.layers.45.self_attn.indexer.k_norm",
"model.layers.45.self_attn.indexer.k_norm.bias",
"model.layers.45.self_attn.indexer.weights_proj",
"model.layers.45.self_attn.indexer.wk",
"model.layers.45.self_attn.indexer.wq_b",
"model.layers.45.self_attn.kv_a_layernorm",
"model.layers.45.self_attn.kv_b_proj",
"model.layers.45.self_attn.q_a_layernorm",
"model.layers.45.shared_head.norm",
"model.layers.5.hc_attn_base",
"model.layers.5.hc_attn_fn",
"model.layers.5.hc_attn_scale",
"model.layers.5.hc_ffn_base",
"model.layers.5.hc_ffn_fn",
"model.layers.5.hc_ffn_scale",
"model.layers.5.input_layernorm",
"model.layers.5.mlp.gate",
"model.layers.5.mlp.gate.e_score_correction_bias",
"model.layers.5.post_attention_layernorm",
"model.layers.5.self_attn.A_log",
"model.layers.5.self_attn.b_proj",
"model.layers.5.self_attn.dt_bias",
"model.layers.5.self_attn.f_a_proj",
"model.layers.5.self_attn.f_b_proj",
"model.layers.5.self_attn.fused_qkvbfg_a_proj",
"model.layers.5.self_attn.g_a_proj",
"model.layers.5.self_attn.g_b_proj",
"model.layers.5.self_attn.k_conv1d",
"model.layers.5.self_attn.k_proj",
"model.layers.5.self_attn.o_norm",
"model.layers.5.self_attn.o_proj",
"model.layers.5.self_attn.q_conv1d",
"model.layers.5.self_attn.q_proj",
"model.layers.5.self_attn.qkv_proj",
"model.layers.5.self_attn.v_conv1d",
"model.layers.5.self_attn.v_proj",
"model.layers.6.hc_attn_base",
"model.layers.6.hc_attn_fn",
"model.layers.6.hc_attn_scale",
"model.layers.6.hc_ffn_base",
"model.layers.6.hc_ffn_fn",
"model.layers.6.hc_ffn_scale",
"model.layers.6.input_layernorm",
"model.layers.6.mlp.gate",
"model.layers.6.mlp.gate.e_score_correction_bias",
"model.layers.6.post_attention_layernorm",
"model.layers.6.self_attn.A_log",
"model.layers.6.self_attn.b_proj",
"model.layers.6.self_attn.dt_bias",
"model.layers.6.self_attn.f_a_proj",
"model.layers.6.self_attn.f_b_proj",
"model.layers.6.self_attn.fused_qkvbfg_a_proj",
"model.layers.6.self_attn.g_a_proj",
"model.layers.6.self_attn.g_b_proj",
"model.layers.6.self_attn.k_conv1d",
"model.layers.6.self_attn.k_proj",
"model.layers.6.self_attn.o_norm",
"model.layers.6.self_attn.o_proj",
"model.layers.6.self_attn.q_conv1d",
"model.layers.6.self_attn.q_proj",
"model.layers.6.self_attn.qkv_proj",
"model.layers.6.self_attn.v_conv1d",
"model.layers.6.self_attn.v_proj",
"model.layers.7.hc_attn_base",
"model.layers.7.hc_attn_fn",
"model.layers.7.hc_attn_scale",
"model.layers.7.hc_ffn_base",
"model.layers.7.hc_ffn_fn",
"model.layers.7.hc_ffn_scale",
"model.layers.7.input_layernorm",
"model.layers.7.mlp.gate",
"model.layers.7.mlp.gate.e_score_correction_bias",
"model.layers.7.post_attention_layernorm",
"model.layers.7.self_attn.indexer.index_kpool_compress_ape",
"model.layers.7.self_attn.indexer.index_kpool_compress_gate",
"model.layers.7.self_attn.indexer.k_norm",
"model.layers.7.self_attn.indexer.k_norm.bias",
"model.layers.7.self_attn.indexer.weights_proj",
"model.layers.7.self_attn.indexer.wk",
"model.layers.7.self_attn.indexer.wq_b",
"model.layers.7.self_attn.kv_a_layernorm",
"model.layers.7.self_attn.kv_b_proj",
"model.layers.7.self_attn.q_a_layernorm",
"model.layers.8.hc_attn_base",
"model.layers.8.hc_attn_fn",
"model.layers.8.hc_attn_scale",
"model.layers.8.hc_ffn_base",
"model.layers.8.hc_ffn_fn",
"model.layers.8.hc_ffn_scale",
"model.layers.8.input_layernorm",
"model.layers.8.mlp.gate",
"model.layers.8.mlp.gate.e_score_correction_bias",
"model.layers.8.post_attention_layernorm",
"model.layers.8.self_attn.A_log",
"model.layers.8.self_attn.b_proj",
"model.layers.8.self_attn.dt_bias",
"model.layers.8.self_attn.f_a_proj",
"model.layers.8.self_attn.f_b_proj",
"model.layers.8.self_attn.fused_qkvbfg_a_proj",
"model.layers.8.self_attn.g_a_proj",
"model.layers.8.self_attn.g_b_proj",
"model.layers.8.self_attn.k_conv1d",
"model.layers.8.self_attn.k_proj",
"model.layers.8.self_attn.o_norm",
"model.layers.8.self_attn.o_proj",
"model.layers.8.self_attn.q_conv1d",
"model.layers.8.self_attn.q_proj",
"model.layers.8.self_attn.qkv_proj",
"model.layers.8.self_attn.v_conv1d",
"model.layers.8.self_attn.v_proj",
"model.layers.9.hc_attn_base",
"model.layers.9.hc_attn_fn",
"model.layers.9.hc_attn_scale",
"model.layers.9.hc_ffn_base",
"model.layers.9.hc_ffn_fn",
"model.layers.9.hc_ffn_scale",
"model.layers.9.input_layernorm",
"model.layers.9.mlp.gate",
"model.layers.9.mlp.gate.e_score_correction_bias",
"model.layers.9.post_attention_layernorm",
"model.layers.9.self_attn.A_log",
"model.layers.9.self_attn.b_proj",
"model.layers.9.self_attn.dt_bias",
"model.layers.9.self_attn.f_a_proj",
"model.layers.9.self_attn.f_b_proj",
"model.layers.9.self_attn.fused_qkvbfg_a_proj",
"model.layers.9.self_attn.g_a_proj",
"model.layers.9.self_attn.g_b_proj",
"model.layers.9.self_attn.k_conv1d",
"model.layers.9.self_attn.k_proj",
"model.layers.9.self_attn.o_norm",
"model.layers.9.self_attn.o_proj",
"model.layers.9.self_attn.q_conv1d",
"model.layers.9.self_attn.q_proj",
"model.layers.9.self_attn.qkv_proj",
"model.layers.9.self_attn.v_conv1d",
"model.layers.9.self_attn.v_proj",
"model.norm",
"model.visual",
"router",
"visual",
"visual.blocks.0.attn.k_norm",
"visual.blocks.0.attn.proj",
"visual.blocks.0.attn.proj.bias",
"visual.blocks.0.attn.q_norm",
"visual.blocks.0.attn.qkv",
"visual.blocks.0.attn.qkv.bias",
"visual.blocks.0.mlp.down_proj",
"visual.blocks.0.mlp.down_proj.bias",
"visual.blocks.0.mlp.gate_proj",
"visual.blocks.0.mlp.gate_proj.bias",
"visual.blocks.0.mlp.up_proj",
"visual.blocks.0.mlp.up_proj.bias",
"visual.blocks.0.norm1",
"visual.blocks.0.norm2",
"visual.blocks.1.attn.k_norm",
"visual.blocks.1.attn.proj",
"visual.blocks.1.attn.proj.bias",
"visual.blocks.1.attn.q_norm",
"visual.blocks.1.attn.qkv",
"visual.blocks.1.attn.qkv.bias",
"visual.blocks.1.mlp.down_proj",
"visual.blocks.1.mlp.down_proj.bias",
"visual.blocks.1.mlp.gate_proj",
"visual.blocks.1.mlp.gate_proj.bias",
"visual.blocks.1.mlp.up_proj",
"visual.blocks.1.mlp.up_proj.bias",
"visual.blocks.1.norm1",
"visual.blocks.1.norm2",
"visual.blocks.10.attn.k_norm",
"visual.blocks.10.attn.proj",
"visual.blocks.10.attn.proj.bias",
"visual.blocks.10.attn.q_norm",
"visual.blocks.10.attn.qkv",
"visual.blocks.10.attn.qkv.bias",
"visual.blocks.10.mlp.down_proj",
"visual.blocks.10.mlp.down_proj.bias",
"visual.blocks.10.mlp.gate_proj",
"visual.blocks.10.mlp.gate_proj.bias",
"visual.blocks.10.mlp.up_proj",
"visual.blocks.10.mlp.up_proj.bias",
"visual.blocks.10.norm1",
"visual.blocks.10.norm2",
"visual.blocks.11.attn.k_norm",
"visual.blocks.11.attn.proj",
"visual.blocks.11.attn.proj.bias",
"visual.blocks.11.attn.q_norm",
"visual.blocks.11.attn.qkv",
"visual.blocks.11.attn.qkv.bias",
"visual.blocks.11.mlp.down_proj",
"visual.blocks.11.mlp.down_proj.bias",
"visual.blocks.11.mlp.gate_proj",
"visual.blocks.11.mlp.gate_proj.bias",
"visual.blocks.11.mlp.up_proj",
"visual.blocks.11.mlp.up_proj.bias",
"visual.blocks.11.norm1",
"visual.blocks.11.norm2",
"visual.blocks.12.attn.k_norm",
"visual.blocks.12.attn.proj",
"visual.blocks.12.attn.proj.bias",
"visual.blocks.12.attn.q_norm",
"visual.blocks.12.attn.qkv",
"visual.blocks.12.attn.qkv.bias",
"visual.blocks.12.mlp.down_proj",
"visual.blocks.12.mlp.down_proj.bias",
"visual.blocks.12.mlp.gate_proj",
"visual.blocks.12.mlp.gate_proj.bias",
"visual.blocks.12.mlp.up_proj",
"visual.blocks.12.mlp.up_proj.bias",
"visual.blocks.12.norm1",
"visual.blocks.12.norm2",
"visual.blocks.13.attn.k_norm",
"visual.blocks.13.attn.proj",
"visual.blocks.13.attn.proj.bias",
"visual.blocks.13.attn.q_norm",
"visual.blocks.13.attn.qkv",
"visual.blocks.13.attn.qkv.bias",
"visual.blocks.13.mlp.down_proj",
"visual.blocks.13.mlp.down_proj.bias",
"visual.blocks.13.mlp.gate_proj",
"visual.blocks.13.mlp.gate_proj.bias",
"visual.blocks.13.mlp.up_proj",
"visual.blocks.13.mlp.up_proj.bias",
"visual.blocks.13.norm1",
"visual.blocks.13.norm2",
"visual.blocks.14.attn.k_norm",
"visual.blocks.14.attn.proj",
"visual.blocks.14.attn.proj.bias",
"visual.blocks.14.attn.q_norm",
"visual.blocks.14.attn.qkv",
"visual.blocks.14.attn.qkv.bias",
"visual.blocks.14.mlp.down_proj",
"visual.blocks.14.mlp.down_proj.bias",
"visual.blocks.14.mlp.gate_proj",
"visual.blocks.14.mlp.gate_proj.bias",
"visual.blocks.14.mlp.up_proj",
"visual.blocks.14.mlp.up_proj.bias",
"visual.blocks.14.norm1",
"visual.blocks.14.norm2",
"visual.blocks.15.attn.k_norm",
"visual.blocks.15.attn.proj",
"visual.blocks.15.attn.proj.bias",
"visual.blocks.15.attn.q_norm",
"visual.blocks.15.attn.qkv",
"visual.blocks.15.attn.qkv.bias",
"visual.blocks.15.mlp.down_proj",
"visual.blocks.15.mlp.down_proj.bias",
"visual.blocks.15.mlp.gate_proj",
"visual.blocks.15.mlp.gate_proj.bias",
"visual.blocks.15.mlp.up_proj",
"visual.blocks.15.mlp.up_proj.bias",
"visual.blocks.15.norm1",
"visual.blocks.15.norm2",
"visual.blocks.16.attn.k_norm",
"visual.blocks.16.attn.proj",
"visual.blocks.16.attn.proj.bias",
"visual.blocks.16.attn.q_norm",
"visual.blocks.16.attn.qkv",
"visual.blocks.16.attn.qkv.bias",
"visual.blocks.16.mlp.down_proj",
"visual.blocks.16.mlp.down_proj.bias",
"visual.blocks.16.mlp.gate_proj",
"visual.blocks.16.mlp.gate_proj.bias",
"visual.blocks.16.mlp.up_proj",
"visual.blocks.16.mlp.up_proj.bias",
"visual.blocks.16.norm1",
"visual.blocks.16.norm2",
"visual.blocks.17.attn.k_norm",
"visual.blocks.17.attn.proj",
"visual.blocks.17.attn.proj.bias",
"visual.blocks.17.attn.q_norm",
"visual.blocks.17.attn.qkv",
"visual.blocks.17.attn.qkv.bias",
"visual.blocks.17.mlp.down_proj",
"visual.blocks.17.mlp.down_proj.bias",
"visual.blocks.17.mlp.gate_proj",
"visual.blocks.17.mlp.gate_proj.bias",
"visual.blocks.17.mlp.up_proj",
"visual.blocks.17.mlp.up_proj.bias",
"visual.blocks.17.norm1",
"visual.blocks.17.norm2",
"visual.blocks.18.attn.k_norm",
"visual.blocks.18.attn.proj",
"visual.blocks.18.attn.proj.bias",
"visual.blocks.18.attn.q_norm",
"visual.blocks.18.attn.qkv",
"visual.blocks.18.attn.qkv.bias",
"visual.blocks.18.mlp.down_proj",
"visual.blocks.18.mlp.down_proj.bias",
"visual.blocks.18.mlp.gate_proj",
"visual.blocks.18.mlp.gate_proj.bias",
"visual.blocks.18.mlp.up_proj",
"visual.blocks.18.mlp.up_proj.bias",
"visual.blocks.18.norm1",
"visual.blocks.18.norm2",
"visual.blocks.19.attn.k_norm",
"visual.blocks.19.attn.proj",
"visual.blocks.19.attn.proj.bias",
"visual.blocks.19.attn.q_norm",
"visual.blocks.19.attn.qkv",
"visual.blocks.19.attn.qkv.bias",
"visual.blocks.19.mlp.down_proj",
"visual.blocks.19.mlp.down_proj.bias",
"visual.blocks.19.mlp.gate_proj",
"visual.blocks.19.mlp.gate_proj.bias",
"visual.blocks.19.mlp.up_proj",
"visual.blocks.19.mlp.up_proj.bias",
"visual.blocks.19.norm1",
"visual.blocks.19.norm2",
"visual.blocks.2.attn.k_norm",
"visual.blocks.2.attn.proj",
"visual.blocks.2.attn.proj.bias",
"visual.blocks.2.attn.q_norm",
"visual.blocks.2.attn.qkv",
"visual.blocks.2.attn.qkv.bias",
"visual.blocks.2.mlp.down_proj",
"visual.blocks.2.mlp.down_proj.bias",
"visual.blocks.2.mlp.gate_proj",
"visual.blocks.2.mlp.gate_proj.bias",
"visual.blocks.2.mlp.up_proj",
"visual.blocks.2.mlp.up_proj.bias",
"visual.blocks.2.norm1",
"visual.blocks.2.norm2",
"visual.blocks.20.attn.k_norm",
"visual.blocks.20.attn.proj",
"visual.blocks.20.attn.proj.bias",
"visual.blocks.20.attn.q_norm",
"visual.blocks.20.attn.qkv",
"visual.blocks.20.attn.qkv.bias",
"visual.blocks.20.mlp.down_proj",
"visual.blocks.20.mlp.down_proj.bias",
"visual.blocks.20.mlp.gate_proj",
"visual.blocks.20.mlp.gate_proj.bias",
"visual.blocks.20.mlp.up_proj",
"visual.blocks.20.mlp.up_proj.bias",
"visual.blocks.20.norm1",
"visual.blocks.20.norm2",
"visual.blocks.21.attn.k_norm",
"visual.blocks.21.attn.proj",
"visual.blocks.21.attn.proj.bias",
"visual.blocks.21.attn.q_norm",
"visual.blocks.21.attn.qkv",
"visual.blocks.21.attn.qkv.bias",
"visual.blocks.21.mlp.down_proj",
"visual.blocks.21.mlp.down_proj.bias",
"visual.blocks.21.mlp.gate_proj",
"visual.blocks.21.mlp.gate_proj.bias",
"visual.blocks.21.mlp.up_proj",
"visual.blocks.21.mlp.up_proj.bias",
"visual.blocks.21.norm1",
"visual.blocks.21.norm2",
"visual.blocks.22.attn.k_norm",
"visual.blocks.22.attn.proj",
"visual.blocks.22.attn.proj.bias",
"visual.blocks.22.attn.q_norm",
"visual.blocks.22.attn.qkv",
"visual.blocks.22.attn.qkv.bias",
"visual.blocks.22.mlp.down_proj",
"visual.blocks.22.mlp.down_proj.bias",
"visual.blocks.22.mlp.gate_proj",
"visual.blocks.22.mlp.gate_proj.bias",
"visual.blocks.22.mlp.up_proj",
"visual.blocks.22.mlp.up_proj.bias",
"visual.blocks.22.norm1",
"visual.blocks.22.norm2",
"visual.blocks.23.attn.k_norm",
"visual.blocks.23.attn.proj",
"visual.blocks.23.attn.proj.bias",
"visual.blocks.23.attn.q_norm",
"visual.blocks.23.attn.qkv",
"visual.blocks.23.attn.qkv.bias",
"visual.blocks.23.mlp.down_proj",
"visual.blocks.23.mlp.down_proj.bias",
"visual.blocks.23.mlp.gate_proj",
"visual.blocks.23.mlp.gate_proj.bias",
"visual.blocks.23.mlp.up_proj",
"visual.blocks.23.mlp.up_proj.bias",
"visual.blocks.23.norm1",
"visual.blocks.23.norm2",
"visual.blocks.3.attn.k_norm",
"visual.blocks.3.attn.proj",
"visual.blocks.3.attn.proj.bias",
"visual.blocks.3.attn.q_norm",
"visual.blocks.3.attn.qkv",
"visual.blocks.3.attn.qkv.bias",
"visual.blocks.3.mlp.down_proj",
"visual.blocks.3.mlp.down_proj.bias",
"visual.blocks.3.mlp.gate_proj",
"visual.blocks.3.mlp.gate_proj.bias",
"visual.blocks.3.mlp.up_proj",
"visual.blocks.3.mlp.up_proj.bias",
"visual.blocks.3.norm1",
"visual.blocks.3.norm2",
"visual.blocks.4.attn.k_norm",
"visual.blocks.4.attn.proj",
"visual.blocks.4.attn.proj.bias",
"visual.blocks.4.attn.q_norm",
"visual.blocks.4.attn.qkv",
"visual.blocks.4.attn.qkv.bias",
"visual.blocks.4.mlp.down_proj",
"visual.blocks.4.mlp.down_proj.bias",
"visual.blocks.4.mlp.gate_proj",
"visual.blocks.4.mlp.gate_proj.bias",
"visual.blocks.4.mlp.up_proj",
"visual.blocks.4.mlp.up_proj.bias",
"visual.blocks.4.norm1",
"visual.blocks.4.norm2",
"visual.blocks.5.attn.k_norm",
"visual.blocks.5.attn.proj",
"visual.blocks.5.attn.proj.bias",
"visual.blocks.5.attn.q_norm",
"visual.blocks.5.attn.qkv",
"visual.blocks.5.attn.qkv.bias",
"visual.blocks.5.mlp.down_proj",
"visual.blocks.5.mlp.down_proj.bias",
"visual.blocks.5.mlp.gate_proj",
"visual.blocks.5.mlp.gate_proj.bias",
"visual.blocks.5.mlp.up_proj",
"visual.blocks.5.mlp.up_proj.bias",
"visual.blocks.5.norm1",
"visual.blocks.5.norm2",
"visual.blocks.6.attn.k_norm",
"visual.blocks.6.attn.proj",
"visual.blocks.6.attn.proj.bias",
"visual.blocks.6.attn.q_norm",
"visual.blocks.6.attn.qkv",
"visual.blocks.6.attn.qkv.bias",
"visual.blocks.6.mlp.down_proj",
"visual.blocks.6.mlp.down_proj.bias",
"visual.blocks.6.mlp.gate_proj",
"visual.blocks.6.mlp.gate_proj.bias",
"visual.blocks.6.mlp.up_proj",
"visual.blocks.6.mlp.up_proj.bias",
"visual.blocks.6.norm1",
"visual.blocks.6.norm2",
"visual.blocks.7.attn.k_norm",
"visual.blocks.7.attn.proj",
"visual.blocks.7.attn.proj.bias",
"visual.blocks.7.attn.q_norm",
"visual.blocks.7.attn.qkv",
"visual.blocks.7.attn.qkv.bias",
"visual.blocks.7.mlp.down_proj",
"visual.blocks.7.mlp.down_proj.bias",
"visual.blocks.7.mlp.gate_proj",
"visual.blocks.7.mlp.gate_proj.bias",
"visual.blocks.7.mlp.up_proj",
"visual.blocks.7.mlp.up_proj.bias",
"visual.blocks.7.norm1",
"visual.blocks.7.norm2",
"visual.blocks.8.attn.k_norm",
"visual.blocks.8.attn.proj",
"visual.blocks.8.attn.proj.bias",
"visual.blocks.8.attn.q_norm",
"visual.blocks.8.attn.qkv",
"visual.blocks.8.attn.qkv.bias",
"visual.blocks.8.mlp.down_proj",
"visual.blocks.8.mlp.down_proj.bias",
"visual.blocks.8.mlp.gate_proj",
"visual.blocks.8.mlp.gate_proj.bias",
"visual.blocks.8.mlp.up_proj",
"visual.blocks.8.mlp.up_proj.bias",
"visual.blocks.8.norm1",
"visual.blocks.8.norm2",
"visual.blocks.9.attn.k_norm",
"visual.blocks.9.attn.proj",
"visual.blocks.9.attn.proj.bias",
"visual.blocks.9.attn.q_norm",
"visual.blocks.9.attn.qkv",
"visual.blocks.9.attn.qkv.bias",
"visual.blocks.9.mlp.down_proj",
"visual.blocks.9.mlp.down_proj.bias",
"visual.blocks.9.mlp.gate_proj",
"visual.blocks.9.mlp.gate_proj.bias",
"visual.blocks.9.mlp.up_proj",
"visual.blocks.9.mlp.up_proj.bias",
"visual.blocks.9.norm1",
"visual.blocks.9.norm2",
"visual.downsample",
"visual.downsample.bias",
"visual.merger.down_proj",
"visual.merger.gate_proj",
"visual.merger.post_projection_norm",
"visual.merger.post_projection_norm.bias",
"visual.merger.proj",
"visual.merger.up_proj",
"visual.patch_embed.proj",
"visual.patch_embed.proj.bias",
"visual.post_layernorm",
"weights_proj"
],
"quant_method": "fp8"
},
"tokenizer_config": {
"eos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>"
}
},
"createdAt": "2026-08-26T21:09:20.000Z",
"disabled": false,
"downloads": 49224,
"gated": false,
"id": "dealignai/GLM-5.3-Flash-UNCENSORED-FP8",
"lastModified": "2026-09-19T16:32:29.000Z",
"likes": 126,
"model-index": null,
"modelId": "dealignai/GLM-5.3-Flash-UNCENSORED-FP8",
"private": false,
"safetensors": {
"parameters": {
"BF16": 6926096640,
"F32": 295518,
"F8_E4M3": 314396639232
},
"total": 321323031390
},
"sha": "d5822b068da8ddb301665b48c58718e6e18a2c3a",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "dealign_logo.png"
},
{
"rfilename": "dealign_mascot.png"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "model-00001-of-00062.safetensors"
},
{
"rfilename": "model-00002-of-00062.safetensors"
},
{
"rfilename": "model-00003-of-00062.safetensors"
},
{
"rfilename": "model-00004-of-00062.safetensors"
},
{
"rfilename": "model-00005-of-00062.safetensors"
},
{
"rfilename": "model-00006-of-00062.safetensors"
},
{
"rfilename": "model-00007-of-00062.safetensors"
},
{
"rfilename": "model-00008-of-00062.safetensors"
},
{
"rfilename": "model-00009-of-00062.safetensors"
},
{
"rfilename": "model-00010-of-00062.safetensors"
},
{
"rfilename": "model-00011-of-00062.safetensors"
},
{
"rfilename": "model-00012-of-00062.safetensors"
},
{
"rfilename": "model-00013-of-00062.safetensors"
},
{
"rfilename": "model-00014-of-00062.safetensors"
},
{
"rfilename": "model-00015-of-00062.safetensors"
},
{
"rfilename": "model-00016-of-00062.safetensors"
},
{
"rfilename": "model-00017-of-00062.safetensors"
},
{
"rfilename": "model-00018-of-00062.safetensors"
},
{
"rfilename": "model-00019-of-00062.safetensors"
},
{
"rfilename": "model-00020-of-00062.safetensors"
},
{
"rfilename": "model-00021-of-00062.safetensors"
},
{
"rfilename": "model-00022-of-00062.safetensors"
},
{
"rfilename": "model-00023-of-00062.safetensors"
},
{
"rfilename": "model-00024-of-00062.safetensors"
},
{
"rfilename": "model-00025-of-00062.safetensors"
},
{
"rfilename": "model-00026-of-00062.safetensors"
},
{
"rfilename": "model-00027-of-00062.safetensors"
},
{
"rfilename": "model-00028-of-00062.safetensors"
},
{
"rfilename": "model-00029-of-00062.safetensors"
},
{
"rfilename": "model-00030-of-00062.safetensors"
},
{
"rfilename": "model-00031-of-00062.safetensors"
},
{
"rfilename": "model-00032-of-00062.safetensors"
},
{
"rfilename": "model-00033-of-00062.safetensors"
},
{
"rfilename": "model-00034-of-00062.safetensors"
},
{
"rfilename": "model-00035-of-00062.safetensors"
},
{
"rfilename": "model-00036-of-00062.safetensors"
},
{
"rfilename": "model-00037-of-00062.safetensors"
},
{
"rfilename": "model-00038-of-00062.safetensors"
},
{
"rfilename": "model-00039-of-00062.safetensors"
},
{
"rfilename": "model-00040-of-00062.safetensors"
},
{
"rfilename": "model-00041-of-00062.safetensors"
},
{
"rfilename": "model-00042-of-00062.safetensors"
},
{
"rfilename": "model-00043-of-00062.safetensors"
},
{
"rfilename": "model-00044-of-00062.safetensors"
},
{
"rfilename": "model-00045-of-00062.safetensors"
},
{
"rfilename": "model-00046-of-00062.safetensors"
},
{
"rfilename": "model-00047-of-00062.safetensors"
},
{
"rfilename": "model-00048-of-00062.safetensors"
},
{
"rfilename": "model-00049-of-00062.safetensors"
},
{
"rfilename": "model-00050-of-00062.safetensors"
},
{
"rfilename": "model-00051-of-00062.safetensors"
},
{
"rfilename": "model-00052-of-00062.safetensors"
},
{
"rfilename": "model-00053-of-00062.safetensors"
},
{
"rfilename": "model-00054-of-00062.safetensors"
},
{
"rfilename": "model-00055-of-00062.safetensors"
},
{
"rfilename": "model-00056-of-00062.safetensors"
},
{
"rfilename": "model-00057-of-00062.safetensors"
},
{
"rfilename": "model-00058-of-00062.safetensors"
},
{
"rfilename": "model-00059-of-00062.safetensors"
},
{
"rfilename": "model-00060-of-00062.safetensors"
},
{
"rfilename": "model-00061-of-00062.safetensors"
},
{
"rfilename": "model-00062-of-00062.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "processor_config.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
}
],
"spaces": [
"tardellirs/model-pulse",
"aquanode/gpu-vram-calculator"
],
"tags": [
"safetensors",
"glm5_next",
"abliterated",
"uncensored",
"crack",
"glm",
"moe",
"fp8",
"vision",
"mtp",
"en",
"base_model:zai-org/GLM-5.3-Flash",
"base_model:quantized:zai-org/GLM-5.3-Flash",
"license:mit",
"region:us"
],
"usedStorage": 505375369250
} | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| downloads | 49224receipt
What the source handed over{
"_asked": "dealignai/GLM-5.3-Flash-UNCENSORED-FP8",
"_id": "6a8f5600e8e799f3299d529f",
"author": "dealignai",
"cardData": {
"base_model": [
"zai-org/GLM-5.3-Flash"
],
"language": [
"en"
],
"license": "mit",
"tags": [
"abliterated",
"uncensored",
"crack",
"glm",
"moe",
"fp8",
"vision",
"mtp"
],
"thumbnail": "dealign_mascot.png"
},
"config": {
"architectures": [
"Glm5NextForConditionalGeneration"
],
"chat_template_jinja": "[gMASK]<sop>\n{%- set effective_reasoning_effort = reasoning_effort if reasoning_effort is defined and reasoning_effort in ['low', 'high'] else 'max' -%}\n{%- if effective_reasoning_effort is not none -%}<|system|>Reasoning Effort: {{ effective_reasoning_effort | capitalize }}{%- endif -%}\n{%- set clear_thinking = clear_thinking if clear_thinking is defined else true -%}\n{%- if tools -%}\n{%- macro tool_to_json(tool) -%}\n {%- set ns_tool = namespace(first=true) -%}\n {{ '{' -}}\n {%- for k, v in tool.items() -%}\n {%- if k != 'defer_loading' and k != 'strict' -%}\n {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}\n {%- set ns_tool.first = false -%}\n \"{{ k }}\": {{ v | tojson(ensure_ascii=False) }}\n {%- endif -%}\n {%- endfor -%}\n {{- '}' -}}\n{%- endmacro -%}\n{%- macro tool_references_to_response(refs) -%}\n {{- '<tool_response><tools>\\n' -}}\n {%- for tr in refs -%}\n {%- for tool in tools -%}\n {%- if 'function' in tool -%}\n {%- set tool = tool['function'] -%}\n {%- endif -%}\n {%- if tool.name == tr.name -%}\n {{- tool_to_json(tool) + '\\n' -}}\n {%- endif -%}\n {%- endfor -%}\n {%- endfor -%}\n {{- '</tools></tool_response>' -}}\n{%- endmacro -%}\n<|system|>\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{% for tool in tools %}\n{%- if 'function' in tool -%}\n {%- set tool = tool['function'] -%}\n{%- endif -%}\n{% if tool.defer_loading is not defined or not tool.defer_loading %}\n{{ tool_to_json(tool) }}\n{% endif %}\n{% endfor %}\n</tools>\n\nFor each function call, output the function name and arguments within the following XML format:\n<tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}\n{%- macro emit_image() -%}<|begin_of_image|><|image|><|end_of_image|>{%- endmacro -%}\n{%- macro emit_video() -%}<|begin_of_video|><|video|><|end_of_video|>{%- endmacro -%}\n{%- macro emit_audio() -%}<|begin_of_audio|><|end_of_audio|>{%- endmacro -%}\n{%- macro visible_text(content) -%}\n {%- if content is string -%}\n {{- content -}}\n {%- elif content is iterable and content is not mapping -%}\n {%- for item in content -%}\n {%- if item is mapping and item.type == 'text' -%}\n {{- item.text -}}\n {%- elif item is string -%}\n {{- item -}}\n {%- elif item is mapping and item.type in ['image', 'image_url'] -%}\n {{- emit_image() -}}\n {%- elif item is mapping and item.type in ['video', 'video_url'] -%}\n {{- emit_video() -}}\n {%- elif item is mapping and item.type in ['audio', 'audio_url', 'input_audio'] -%}\n {{- emit_audio() -}}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{- content }}\n {%- endif -%}\n{%- endmacro -%}\n{%- macro tool_response(text) -%}\n{{- '<tool_response>' + text + '</tool_response>' -}}\n{%- endmacro -%}\n{%- macro render_tool_response(m) -%}\n{%- if m.content is string -%}\n {{- tool_response(m.content) -}}\n{%- elif m.content and m.content is not mapping and m.content.0.type == \"tool_reference\" -%}\n {{- tool_references_to_response(m.content) -}}\n{%- elif is_list_of_outputs(m) -%}\n {%- for tr in m.content -%}\n {%- if tr.output is iterable and tr.output is not string and tr.output is not mapping and tr.output and tr.output.0.type == \"tool_reference\" -%}\n {{- tool_references_to_response(tr.output) -}}\n {%- else -%}\n {{- tool_response(visible_text(tr.output)) -}}\n {%- endif -%}\n {%- endfor -%}\n{%- else -%}\n {{- tool_response(visible_text(m.content)) -}}\n{%- endif -%}\n{%- endmacro -%}\n{%- macro id_of(obj) -%}\n {%- if obj.tool_call_id -%}\n {{- obj.tool_call_id -}}\n {%- elif obj.id -%}\n {{- obj.id -}}\n {%- endif -%}\n{%- endmacro -%}\n{%- macro is_list_of_outputs(m) -%}\n {%- if m.content and m.content.0.output is defined -%}1{%- endif -%}\n{%- endmacro -%}\n{%- macro has_dup_tool_result_id(lo, hi, target) -%}\n {%- set ns_cnt = namespace(n=0) -%}\n {%- for k in range(lo, hi + 1) -%}\n {%- set m = messages[k] -%}\n {%- if is_list_of_outputs(m) -%}\n {%- for entry in m.content -%}\n {%- if id_of(entry) == target -%}\n {%- set ns_cnt.n = ns_cnt.n + 1 -%}\n {%- endif -%}\n {%- endfor -%}\n {%- elif id_of(m) == target -%}\n {%- set ns_cnt.n = ns_cnt.n + 1 -%}\n {%- endif -%}\n {%- if ns_cnt.n > 1 -%}{%- break -%}{%- endif -%}\n {%- endfor -%}\n {%- if ns_cnt.n > 1 -%}1{%- endif -%}\n{%- endmacro -%}\n{%- macro tc_id_exists(tcs, target) -%}\n {%- set ns_f = namespace(found=false) -%}\n {%- for tc in tcs -%}\n {%- if id_of(tc) == target -%}\n {%- set ns_f.found = true -%}\n {%- break -%}\n {%- endif -%}\n {%- endfor -%}\n {%- if ns_f.found -%}1{%- endif -%}\n{%- endmacro -%}\n{%- set ns = namespace(last_user_index=-1) -%}\n{%- for m in messages %}\n {%- if m.role == 'user' %}\n {%- set ns.last_user_index = loop.index0 -%}\n {%- endif %}\n{%- endfor %}\n{%- for m in messages -%}\n{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}\n{%- elif m.role == 'assistant' -%}\n<|assistant|>\n{%- set content = visible_text(m.content) %}\n{%- if m.reasoning_content is string %}\n {%- set reasoning_content = m.reasoning_content %}\n{%- elif '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}\n {%- set content = content.split('</think>')[-1] %}\n{%- endif %}\n{%- if (not clear_thinking or loop.index0 > ns.last_user_index) and reasoning_content is defined -%}\n{{ '<think>' + reasoning_content + '</think>'}}\n{%- else -%}\n{{ '<think></think>' }}\n{%- endif -%}\n{%- if content.strip() -%}\n{{ content.strip() }}\n{%- endif -%}\n{% if m.tool_calls %}\n{% for tc in m.tool_calls %}\n{%- if tc.function %}\n {%- set tc = tc.function %}\n{%- endif %}\n{{- '<tool_call>' + tc.name -}}\n{% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}\n{% endif %}\n{%- elif m.role == 'tool' -%}\n{%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|observation|>' -}}\n {%- set block_start = loop.index0 -%}\n {%- set ns_blk = namespace(end=block_start) -%}\n {%- for j in range(block_start, messages|length) -%}\n {%- if messages[j].role == 'tool' -%}\n {%- set ns_blk.end = j -%}\n {%- else -%}\n {%- break -%}\n {%- endif -%}\n {%- endfor -%}\n {%- set ns_a = namespace(tool_calls=none) -%}\n {%- if block_start > 0 and messages[block_start - 1].role == 'assistant' and messages[block_start - 1].tool_calls -%}\n {%- set ns_a.tool_calls = messages[block_start - 1].tool_calls -%}\n {%- endif -%}\n {%- set ns_chk = namespace(can_sort=true) -%}\n {%- if not ns_a.tool_calls -%}\n {%- set ns_chk.can_sort = false -%}\n {%- else -%}\n {%- for k in range(block_start, ns_blk.end + 1) -%}\n {%- set m = messages[k] -%}\n {%- if is_list_of_outputs(m) -%}\n {%- for entry in m.content -%}\n {%- set eid = id_of(entry) -%}\n {%- if not eid -%}\n {%- set ns_chk.can_sort = false -%}\n {%- elif has_dup_tool_result_id(block_start, ns_blk.end, eid) -%}\n {%- set ns_chk.can_sort = false -%}\n {%- elif not tc_id_exists(ns_a.tool_calls, eid) -%}\n {%- set ns_chk.can_sort = false -%}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {%- set tk_id = id_of(m) -%}\n {%- if not tk_id -%}\n {%- set ns_chk.can_sort = false -%}\n {%- elif has_dup_tool_result_id(block_start, ns_blk.end, tk_id) -%}\n {%- set ns_chk.can_sort = false -%}\n {%- elif not tc_id_exists(ns_a.tool_calls, tk_id) -%}\n {%- set ns_chk.can_sort = false -%}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n {%- for i in range(ns_a.tool_calls | length) -%}\n {%- set tc_id = id_of(ns_a.tool_calls[i]) -%}\n {%- if not tc_id -%}\n {%- set ns_chk.can_sort = false -%}\n {%- endif -%}\n {%- for j in range(i + 1, ns_a.tool_calls | length) -%}\n {%- if id_of(ns_a.tool_calls[j]) == tc_id -%}\n {%- set ns_chk.can_sort = false -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endfor -%}\n {%- endif -%}\n {%- if ns_chk.can_sort -%}\n {%- for tc in ns_a.tool_calls -%}\n {%- set tc_id = id_of(tc) -%}\n {%- for k in range(block_start, ns_blk.end + 1) -%}\n {%- set m = messages[k] -%}\n {%- if is_list_of_outputs(m) -%}\n {%- for entry in m.content -%}\n {%- set eid = id_of(entry) -%}\n {%- if eid == tc_id -%}\n {%- if entry.output is iterable and entry.output is not string and entry.output is not mapping and entry.output and entry.output.0.type == \"tool_reference\" -%}\n {{- tool_references_to_response(entry.output) -}}\n {%- else -%}\n {{- tool_response(visible_text(entry.output)) -}}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n{%- else -%}\n {%- set tk_id = id_of(m) -%}\n {%- if tk_id == tc_id -%}\n {{- render_tool_response(m) -}}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endfor -%}\n {%- else -%}\n {%- for k in range(block_start, ns_blk.end + 1) -%}\n {{- render_tool_response(messages[k]) -}}\n {%- endfor -%}\n {%- endif -%}\n{% endif -%}\n{%- elif m.role == 'system' -%}\n<|system|>{{ visible_text(m.content) }}\n{%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n <|assistant|>{{- '<think>' -}}\n{%- endif -%}\n",
"model_type": "glm5_next",
"quantization_config": {
"modules_to_not_convert": [
"attn_mha",
"attn_mqa",
"dt_bias",
"hyper_connection",
"lm_head",
"mapping_proj",
"model.embed_tokens",
"model.layers.0.hc_attn_base",
"model.layers.0.hc_attn_fn",
"model.layers.0.hc_attn_scale",
"model.layers.0.hc_ffn_base",
"model.layers.0.hc_ffn_fn",
"model.layers.0.hc_ffn_scale",
"model.layers.0.input_layernorm",
"model.layers.0.post_attention_layernorm",
"model.layers.0.self_attn.A_log",
"model.layers.0.self_attn.b_proj",
"model.layers.0.self_attn.dt_bias",
"model.layers.0.self_attn.f_a_proj",
"model.layers.0.self_attn.f_b_proj",
"model.layers.0.self_attn.fused_qkvbfg_a_proj",
"model.layers.0.self_attn.g_a_proj",
"model.layers.0.self_attn.g_b_proj",
"model.layers.0.self_attn.k_conv1d",
"model.layers.0.self_attn.k_proj",
"model.layers.0.self_attn.o_norm",
"model.layers.0.self_attn.o_proj",
"model.layers.0.self_attn.q_conv1d",
"model.layers.0.self_attn.q_proj",
"model.layers.0.self_attn.qkv_proj",
"model.layers.0.self_attn.v_conv1d",
"model.layers.0.self_attn.v_proj",
"model.layers.1.hc_attn_base",
"model.layers.1.hc_attn_fn",
"model.layers.1.hc_attn_scale",
"model.layers.1.hc_ffn_base",
"model.layers.1.hc_ffn_fn",
"model.layers.1.hc_ffn_scale",
"model.layers.1.input_layernorm",
"model.layers.1.post_attention_layernorm",
"model.layers.1.self_attn.A_log",
"model.layers.1.self_attn.b_proj",
"model.layers.1.self_attn.dt_bias",
"model.layers.1.self_attn.f_a_proj",
"model.layers.1.self_attn.f_b_proj",
"model.layers.1.self_attn.fused_qkvbfg_a_proj",
"model.layers.1.self_attn.g_a_proj",
"model.layers.1.self_attn.g_b_proj",
"model.layers.1.self_attn.k_conv1d",
"model.layers.1.self_attn.k_proj",
"model.layers.1.self_attn.o_norm",
"model.layers.1.self_attn.o_proj",
"model.layers.1.self_attn.q_conv1d",
"model.layers.1.self_attn.q_proj",
"model.layers.1.self_attn.qkv_proj",
"model.layers.1.self_attn.v_conv1d",
"model.layers.1.self_attn.v_proj",
"model.layers.10.hc_attn_base",
"model.layers.10.hc_attn_fn",
"model.layers.10.hc_attn_scale",
"model.layers.10.hc_ffn_base",
"model.layers.10.hc_ffn_fn",
"model.layers.10.hc_ffn_scale",
"model.layers.10.input_layernorm",
"model.layers.10.mlp.gate",
"model.layers.10.mlp.gate.e_score_correction_bias",
"model.layers.10.post_attention_layernorm",
"model.layers.10.self_attn.A_log",
"model.layers.10.self_attn.b_proj",
"model.layers.10.self_attn.dt_bias",
"model.layers.10.self_attn.f_a_proj",
"model.layers.10.self_attn.f_b_proj",
"model.layers.10.self_attn.fused_qkvbfg_a_proj",
"model.layers.10.self_attn.g_a_proj",
"model.layers.10.self_attn.g_b_proj",
"model.layers.10.self_attn.k_conv1d",
"model.layers.10.self_attn.k_proj",
"model.layers.10.self_attn.o_norm",
"model.layers.10.self_attn.o_proj",
"model.layers.10.self_attn.q_conv1d",
"model.layers.10.self_attn.q_proj",
"model.layers.10.self_attn.qkv_proj",
"model.layers.10.self_attn.v_conv1d",
"model.layers.10.self_attn.v_proj",
"model.layers.11.hc_attn_base",
"model.layers.11.hc_attn_fn",
"model.layers.11.hc_attn_scale",
"model.layers.11.hc_ffn_base",
"model.layers.11.hc_ffn_fn",
"model.layers.11.hc_ffn_scale",
"model.layers.11.input_layernorm",
"model.layers.11.mlp.gate",
"model.layers.11.mlp.gate.e_score_correction_bias",
"model.layers.11.post_attention_layernorm",
"model.layers.11.self_attn.indexer.index_kpool_compress_ape",
"model.layers.11.self_attn.indexer.index_kpool_compress_gate",
"model.layers.11.self_attn.indexer.k_norm",
"model.layers.11.self_attn.indexer.k_norm.bias",
"model.layers.11.self_attn.indexer.weights_proj",
"model.layers.11.self_attn.indexer.wk",
"model.layers.11.self_attn.indexer.wq_b",
"model.layers.11.self_attn.kv_a_layernorm",
"model.layers.11.self_attn.kv_b_proj",
"model.layers.11.self_attn.q_a_layernorm",
"model.layers.12.hc_attn_base",
"model.layers.12.hc_attn_fn",
"model.layers.12.hc_attn_scale",
"model.layers.12.hc_ffn_base",
"model.layers.12.hc_ffn_fn",
"model.layers.12.hc_ffn_scale",
"model.layers.12.input_layernorm",
"model.layers.12.mlp.gate",
"model.layers.12.mlp.gate.e_score_correction_bias",
"model.layers.12.post_attention_layernorm",
"model.layers.12.self_attn.A_log",
"model.layers.12.self_attn.b_proj",
"model.layers.12.self_attn.dt_bias",
"model.layers.12.self_attn.f_a_proj",
"model.layers.12.self_attn.f_b_proj",
"model.layers.12.self_attn.fused_qkvbfg_a_proj",
"model.layers.12.self_attn.g_a_proj",
"model.layers.12.self_attn.g_b_proj",
"model.layers.12.self_attn.k_conv1d",
"model.layers.12.self_attn.k_proj",
"model.layers.12.self_attn.o_norm",
"model.layers.12.self_attn.o_proj",
"model.layers.12.self_attn.q_conv1d",
"model.layers.12.self_attn.q_proj",
"model.layers.12.self_attn.qkv_proj",
"model.layers.12.self_attn.v_conv1d",
"model.layers.12.self_attn.v_proj",
"model.layers.13.hc_attn_base",
"model.layers.13.hc_attn_fn",
"model.layers.13.hc_attn_scale",
"model.layers.13.hc_ffn_base",
"model.layers.13.hc_ffn_fn",
"model.layers.13.hc_ffn_scale",
"model.layers.13.input_layernorm",
"model.layers.13.mlp.gate",
"model.layers.13.mlp.gate.e_score_correction_bias",
"model.layers.13.post_attention_layernorm",
"model.layers.13.self_attn.A_log",
"model.layers.13.self_attn.b_proj",
"model.layers.13.self_attn.dt_bias",
"model.layers.13.self_attn.f_a_proj",
"model.layers.13.self_attn.f_b_proj",
"model.layers.13.self_attn.fused_qkvbfg_a_proj",
"model.layers.13.self_attn.g_a_proj",
"model.layers.13.self_attn.g_b_proj",
"model.layers.13.self_attn.k_conv1d",
"model.layers.13.self_attn.k_proj",
"model.layers.13.self_attn.o_norm",
"model.layers.13.self_attn.o_proj",
"model.layers.13.self_attn.q_conv1d",
"model.layers.13.self_attn.q_proj",
"model.layers.13.self_attn.qkv_proj",
"model.layers.13.self_attn.v_conv1d",
"model.layers.13.self_attn.v_proj",
"model.layers.14.hc_attn_base",
"model.layers.14.hc_attn_fn",
"model.layers.14.hc_attn_scale",
"model.layers.14.hc_ffn_base",
"model.layers.14.hc_ffn_fn",
"model.layers.14.hc_ffn_scale",
"model.layers.14.input_layernorm",
"model.layers.14.mlp.gate",
"model.layers.14.mlp.gate.e_score_correction_bias",
"model.layers.14.post_attention_layernorm",
"model.layers.14.self_attn.A_log",
"model.layers.14.self_attn.b_proj",
"model.layers.14.self_attn.dt_bias",
"model.layers.14.self_attn.f_a_proj",
"model.layers.14.self_attn.f_b_proj",
"model.layers.14.self_attn.fused_qkvbfg_a_proj",
"model.layers.14.self_attn.g_a_proj",
"model.layers.14.self_attn.g_b_proj",
"model.layers.14.self_attn.k_conv1d",
"model.layers.14.self_attn.k_proj",
"model.layers.14.self_attn.o_norm",
"model.layers.14.self_attn.o_proj",
"model.layers.14.self_attn.q_conv1d",
"model.layers.14.self_attn.q_proj",
"model.layers.14.self_attn.qkv_proj",
"model.layers.14.self_attn.v_conv1d",
"model.layers.14.self_attn.v_proj",
"model.layers.15.hc_attn_base",
"model.layers.15.hc_attn_fn",
"model.layers.15.hc_attn_scale",
"model.layers.15.hc_ffn_base",
"model.layers.15.hc_ffn_fn",
"model.layers.15.hc_ffn_scale",
"model.layers.15.input_layernorm",
"model.layers.15.mlp.gate",
"model.layers.15.mlp.gate.e_score_correction_bias",
"model.layers.15.post_attention_layernorm",
"model.layers.15.self_attn.indexer.index_kpool_compress_ape",
"model.layers.15.self_attn.indexer.index_kpool_compress_gate",
"model.layers.15.self_attn.indexer.k_norm",
"model.layers.15.self_attn.indexer.k_norm.bias",
"model.layers.15.self_attn.indexer.weights_proj",
"model.layers.15.self_attn.indexer.wk",
"model.layers.15.self_attn.indexer.wq_b",
"model.layers.15.self_attn.kv_a_layernorm",
"model.layers.15.self_attn.kv_b_proj",
"model.layers.15.self_attn.q_a_layernorm",
"model.layers.16.hc_attn_base",
"model.layers.16.hc_attn_fn",
"model.layers.16.hc_attn_scale",
"model.layers.16.hc_ffn_base",
"model.layers.16.hc_ffn_fn",
"model.layers.16.hc_ffn_scale",
"model.layers.16.input_layernorm",
"model.layers.16.mlp.gate",
"model.layers.16.mlp.gate.e_score_correction_bias",
"model.layers.16.post_attention_layernorm",
"model.layers.16.self_attn.A_log",
"model.layers.16.self_attn.b_proj",
"model.layers.16.self_attn.dt_bias",
"model.layers.16.self_attn.f_a_proj",
"model.layers.16.self_attn.f_b_proj",
"model.layers.16.self_attn.fused_qkvbfg_a_proj",
"model.layers.16.self_attn.g_a_proj",
"model.layers.16.self_attn.g_b_proj",
"model.layers.16.self_attn.k_conv1d",
"model.layers.16.self_attn.k_proj",
"model.layers.16.self_attn.o_norm",
"model.layers.16.self_attn.o_proj",
"model.layers.16.self_attn.q_conv1d",
"model.layers.16.self_attn.q_proj",
"model.layers.16.self_attn.qkv_proj",
"model.layers.16.self_attn.v_conv1d",
"model.layers.16.self_attn.v_proj",
"model.layers.17.hc_attn_base",
"model.layers.17.hc_attn_fn",
"model.layers.17.hc_attn_scale",
"model.layers.17.hc_ffn_base",
"model.layers.17.hc_ffn_fn",
"model.layers.17.hc_ffn_scale",
"model.layers.17.input_layernorm",
"model.layers.17.mlp.gate",
"model.layers.17.mlp.gate.e_score_correction_bias",
"model.layers.17.post_attention_layernorm",
"model.layers.17.self_attn.A_log",
"model.layers.17.self_attn.b_proj",
"model.layers.17.self_attn.dt_bias",
"model.layers.17.self_attn.f_a_proj",
"model.layers.17.self_attn.f_b_proj",
"model.layers.17.self_attn.fused_qkvbfg_a_proj",
"model.layers.17.self_attn.g_a_proj",
"model.layers.17.self_attn.g_b_proj",
"model.layers.17.self_attn.k_conv1d",
"model.layers.17.self_attn.k_proj",
"model.layers.17.self_attn.o_norm",
"model.layers.17.self_attn.o_proj",
"model.layers.17.self_attn.q_conv1d",
"model.layers.17.self_attn.q_proj",
"model.layers.17.self_attn.qkv_proj",
"model.layers.17.self_attn.v_conv1d",
"model.layers.17.self_attn.v_proj",
"model.layers.18.hc_attn_base",
"model.layers.18.hc_attn_fn",
"model.layers.18.hc_attn_scale",
"model.layers.18.hc_ffn_base",
"model.layers.18.hc_ffn_fn",
"model.layers.18.hc_ffn_scale",
"model.layers.18.input_layernorm",
"model.layers.18.mlp.gate",
"model.layers.18.mlp.gate.e_score_correction_bias",
"model.layers.18.post_attention_layernorm",
"model.layers.18.self_attn.A_log",
"model.layers.18.self_attn.b_proj",
"model.layers.18.self_attn.dt_bias",
"model.layers.18.self_attn.f_a_proj",
"model.layers.18.self_attn.f_b_proj",
"model.layers.18.self_attn.fused_qkvbfg_a_proj",
"model.layers.18.self_attn.g_a_proj",
"model.layers.18.self_attn.g_b_proj",
"model.layers.18.self_attn.k_conv1d",
"model.layers.18.self_attn.k_proj",
"model.layers.18.self_attn.o_norm",
"model.layers.18.self_attn.o_proj",
"model.layers.18.self_attn.q_conv1d",
"model.layers.18.self_attn.q_proj",
"model.layers.18.self_attn.qkv_proj",
"model.layers.18.self_attn.v_conv1d",
"model.layers.18.self_attn.v_proj",
"model.layers.19.hc_attn_base",
"model.layers.19.hc_attn_fn",
"model.layers.19.hc_attn_scale",
"model.layers.19.hc_ffn_base",
"model.layers.19.hc_ffn_fn",
"model.layers.19.hc_ffn_scale",
"model.layers.19.input_layernorm",
"model.layers.19.mlp.gate",
"model.layers.19.mlp.gate.e_score_correction_bias",
"model.layers.19.post_attention_layernorm",
"model.layers.19.self_attn.indexer.index_kpool_compress_ape",
"model.layers.19.self_attn.indexer.index_kpool_compress_gate",
"model.layers.19.self_attn.indexer.k_norm",
"model.layers.19.self_attn.indexer.k_norm.bias",
"model.layers.19.self_attn.indexer.weights_proj",
"model.layers.19.self_attn.indexer.wk",
"model.layers.19.self_attn.indexer.wq_b",
"model.layers.19.self_attn.kv_a_layernorm",
"model.layers.19.self_attn.kv_b_proj",
"model.layers.19.self_attn.q_a_layernorm",
"model.layers.2.hc_attn_base",
"model.layers.2.hc_attn_fn",
"model.layers.2.hc_attn_scale",
"model.layers.2.hc_ffn_base",
"model.layers.2.hc_ffn_fn",
"model.layers.2.hc_ffn_scale",
"model.layers.2.input_layernorm",
"model.layers.2.post_attention_layernorm",
"model.layers.2.self_attn.A_log",
"model.layers.2.self_attn.b_proj",
"model.layers.2.self_attn.dt_bias",
"model.layers.2.self_attn.f_a_proj",
"model.layers.2.self_attn.f_b_proj",
"model.layers.2.self_attn.fused_qkvbfg_a_proj",
"model.layers.2.self_attn.g_a_proj",
"model.layers.2.self_attn.g_b_proj",
"model.layers.2.self_attn.k_conv1d",
"model.layers.2.self_attn.k_proj",
"model.layers.2.self_attn.o_norm",
"model.layers.2.self_attn.o_proj",
"model.layers.2.self_attn.q_conv1d",
"model.layers.2.self_attn.q_proj",
"model.layers.2.self_attn.qkv_proj",
"model.layers.2.self_attn.v_conv1d",
"model.layers.2.self_attn.v_proj",
"model.layers.20.hc_attn_base",
"model.layers.20.hc_attn_fn",
"model.layers.20.hc_attn_scale",
"model.layers.20.hc_ffn_base",
"model.layers.20.hc_ffn_fn",
"model.layers.20.hc_ffn_scale",
"model.layers.20.input_layernorm",
"model.layers.20.mlp.gate",
"model.layers.20.mlp.gate.e_score_correction_bias",
"model.layers.20.post_attention_layernorm",
"model.layers.20.self_attn.A_log",
"model.layers.20.self_attn.b_proj",
"model.layers.20.self_attn.dt_bias",
"model.layers.20.self_attn.f_a_proj",
"model.layers.20.self_attn.f_b_proj",
"model.layers.20.self_attn.fused_qkvbfg_a_proj",
"model.layers.20.self_attn.g_a_proj",
"model.layers.20.self_attn.g_b_proj",
"model.layers.20.self_attn.k_conv1d",
"model.layers.20.self_attn.k_proj",
"model.layers.20.self_attn.o_norm",
"model.layers.20.self_attn.o_proj",
"model.layers.20.self_attn.q_conv1d",
"model.layers.20.self_attn.q_proj",
"model.layers.20.self_attn.qkv_proj",
"model.layers.20.self_attn.v_conv1d",
"model.layers.20.self_attn.v_proj",
"model.layers.21.hc_attn_base",
"model.layers.21.hc_attn_fn",
"model.layers.21.hc_attn_scale",
"model.layers.21.hc_ffn_base",
"model.layers.21.hc_ffn_fn",
"model.layers.21.hc_ffn_scale",
"model.layers.21.input_layernorm",
"model.layers.21.mlp.gate",
"model.layers.21.mlp.gate.e_score_correction_bias",
"model.layers.21.post_attention_layernorm",
"model.layers.21.self_attn.A_log",
"model.layers.21.self_attn.b_proj",
"model.layers.21.self_attn.dt_bias",
"model.layers.21.self_attn.f_a_proj",
"model.layers.21.self_attn.f_b_proj",
"model.layers.21.self_attn.fused_qkvbfg_a_proj",
"model.layers.21.self_attn.g_a_proj",
"model.layers.21.self_attn.g_b_proj",
"model.layers.21.self_attn.k_conv1d",
"model.layers.21.self_attn.k_proj",
"model.layers.21.self_attn.o_norm",
"model.layers.21.self_attn.o_proj",
"model.layers.21.self_attn.q_conv1d",
"model.layers.21.self_attn.q_proj",
"model.layers.21.self_attn.qkv_proj",
"model.layers.21.self_attn.v_conv1d",
"model.layers.21.self_attn.v_proj",
"model.layers.22.hc_attn_base",
"model.layers.22.hc_attn_fn",
"model.layers.22.hc_attn_scale",
"model.layers.22.hc_ffn_base",
"model.layers.22.hc_ffn_fn",
"model.layers.22.hc_ffn_scale",
"model.layers.22.input_layernorm",
"model.layers.22.mlp.gate",
"model.layers.22.mlp.gate.e_score_correction_bias",
"model.layers.22.post_attention_layernorm",
"model.layers.22.self_attn.A_log",
"model.layers.22.self_attn.b_proj",
"model.layers.22.self_attn.dt_bias",
"model.layers.22.self_attn.f_a_proj",
"model.layers.22.self_attn.f_b_proj",
"model.layers.22.self_attn.fused_qkvbfg_a_proj",
"model.layers.22.self_attn.g_a_proj",
"model.layers.22.self_attn.g_b_proj",
"model.layers.22.self_attn.k_conv1d",
"model.layers.22.self_attn.k_proj",
"model.layers.22.self_attn.o_norm",
"model.layers.22.self_attn.o_proj",
"model.layers.22.self_attn.q_conv1d",
"model.layers.22.self_attn.q_proj",
"model.layers.22.self_attn.qkv_proj",
"model.layers.22.self_attn.v_conv1d",
"model.layers.22.self_attn.v_proj",
"model.layers.23.hc_attn_base",
"model.layers.23.hc_attn_fn",
"model.layers.23.hc_attn_scale",
"model.layers.23.hc_ffn_base",
"model.layers.23.hc_ffn_fn",
"model.layers.23.hc_ffn_scale",
"model.layers.23.input_layernorm",
"model.layers.23.mlp.gate",
"model.layers.23.mlp.gate.e_score_correction_bias",
"model.layers.23.post_attention_layernorm",
"model.layers.23.self_attn.indexer.index_kpool_compress_ape",
"model.layers.23.self_attn.indexer.index_kpool_compress_gate",
"model.layers.23.self_attn.indexer.k_norm",
"model.layers.23.self_attn.indexer.k_norm.bias",
"model.layers.23.self_attn.indexer.weights_proj",
"model.layers.23.self_attn.indexer.wk",
"model.layers.23.self_attn.indexer.wq_b",
"model.layers.23.self_attn.kv_a_layernorm",
"model.layers.23.self_attn.kv_b_proj",
"model.layers.23.self_attn.q_a_layernorm",
"model.layers.24.hc_attn_base",
"model.layers.24.hc_attn_fn",
"model.layers.24.hc_attn_scale",
"model.layers.24.hc_ffn_base",
"model.layers.24.hc_ffn_fn",
"model.layers.24.hc_ffn_scale",
"model.layers.24.input_layernorm",
"model.layers.24.mlp.gate",
"model.layers.24.mlp.gate.e_score_correction_bias",
"model.layers.24.post_attention_layernorm",
"model.layers.24.self_attn.A_log",
"model.layers.24.self_attn.b_proj",
"model.layers.24.self_attn.dt_bias",
"model.layers.24.self_attn.f_a_proj",
"model.layers.24.self_attn.f_b_proj",
"model.layers.24.self_attn.fused_qkvbfg_a_proj",
"model.layers.24.self_attn.g_a_proj",
"model.layers.24.self_attn.g_b_proj",
"model.layers.24.self_attn.k_conv1d",
"model.layers.24.self_attn.k_proj",
"model.layers.24.self_attn.o_norm",
"model.layers.24.self_attn.o_proj",
"model.layers.24.self_attn.q_conv1d",
"model.layers.24.self_attn.q_proj",
"model.layers.24.self_attn.qkv_proj",
"model.layers.24.self_attn.v_conv1d",
"model.layers.24.self_attn.v_proj",
"model.layers.25.hc_attn_base",
"model.layers.25.hc_attn_fn",
"model.layers.25.hc_attn_scale",
"model.layers.25.hc_ffn_base",
"model.layers.25.hc_ffn_fn",
"model.layers.25.hc_ffn_scale",
"model.layers.25.input_layernorm",
"model.layers.25.mlp.gate",
"model.layers.25.mlp.gate.e_score_correction_bias",
"model.layers.25.post_attention_layernorm",
"model.layers.25.self_attn.A_log",
"model.layers.25.self_attn.b_proj",
"model.layers.25.self_attn.dt_bias",
"model.layers.25.self_attn.f_a_proj",
"model.layers.25.self_attn.f_b_proj",
"model.layers.25.self_attn.fused_qkvbfg_a_proj",
"model.layers.25.self_attn.g_a_proj",
"model.layers.25.self_attn.g_b_proj",
"model.layers.25.self_attn.k_conv1d",
"model.layers.25.self_attn.k_proj",
"model.layers.25.self_attn.o_norm",
"model.layers.25.self_attn.o_proj",
"model.layers.25.self_attn.q_conv1d",
"model.layers.25.self_attn.q_proj",
"model.layers.25.self_attn.qkv_proj",
"model.layers.25.self_attn.v_conv1d",
"model.layers.25.self_attn.v_proj",
"model.layers.26.hc_attn_base",
"model.layers.26.hc_attn_fn",
"model.layers.26.hc_attn_scale",
"model.layers.26.hc_ffn_base",
"model.layers.26.hc_ffn_fn",
"model.layers.26.hc_ffn_scale",
"model.layers.26.input_layernorm",
"model.layers.26.mlp.gate",
"model.layers.26.mlp.gate.e_score_correction_bias",
"model.layers.26.post_attention_layernorm",
"model.layers.26.self_attn.A_log",
"model.layers.26.self_attn.b_proj",
"model.layers.26.self_attn.dt_bias",
"model.layers.26.self_attn.f_a_proj",
"model.layers.26.self_attn.f_b_proj",
"model.layers.26.self_attn.fused_qkvbfg_a_proj",
"model.layers.26.self_attn.g_a_proj",
"model.layers.26.self_attn.g_b_proj",
"model.layers.26.self_attn.k_conv1d",
"model.layers.26.self_attn.k_proj",
"model.layers.26.self_attn.o_norm",
"model.layers.26.self_attn.o_proj",
"model.layers.26.self_attn.q_conv1d",
"model.layers.26.self_attn.q_proj",
"model.layers.26.self_attn.qkv_proj",
"model.layers.26.self_attn.v_conv1d",
"model.layers.26.self_attn.v_proj",
"model.layers.27.hc_attn_base",
"model.layers.27.hc_attn_fn",
"model.layers.27.hc_attn_scale",
"model.layers.27.hc_ffn_base",
"model.layers.27.hc_ffn_fn",
"model.layers.27.hc_ffn_scale",
"model.layers.27.input_layernorm",
"model.layers.27.mlp.gate",
"model.layers.27.mlp.gate.e_score_correction_bias",
"model.layers.27.post_attention_layernorm",
"model.layers.27.self_attn.indexer.index_kpool_compress_ape",
"model.layers.27.self_attn.indexer.index_kpool_compress_gate",
"model.layers.27.self_attn.indexer.k_norm",
"model.layers.27.self_attn.indexer.k_norm.bias",
"model.layers.27.self_attn.indexer.weights_proj",
"model.layers.27.self_attn.indexer.wk",
"model.layers.27.self_attn.indexer.wq_b",
"model.layers.27.self_attn.kv_a_layernorm",
"model.layers.27.self_attn.kv_b_proj",
"model.layers.27.self_attn.q_a_layernorm",
"model.layers.28.hc_attn_base",
"model.layers.28.hc_attn_fn",
"model.layers.28.hc_attn_scale",
"model.layers.28.hc_ffn_base",
"model.layers.28.hc_ffn_fn",
"model.layers.28.hc_ffn_scale",
"model.layers.28.input_layernorm",
"model.layers.28.mlp.gate",
"model.layers.28.mlp.gate.e_score_correction_bias",
"model.layers.28.post_attention_layernorm",
"model.layers.28.self_attn.A_log",
"model.layers.28.self_attn.b_proj",
"model.layers.28.self_attn.dt_bias",
"model.layers.28.self_attn.f_a_proj",
"model.layers.28.self_attn.f_b_proj",
"model.layers.28.self_attn.fused_qkvbfg_a_proj",
"model.layers.28.self_attn.g_a_proj",
"model.layers.28.self_attn.g_b_proj",
"model.layers.28.self_attn.k_conv1d",
"model.layers.28.self_attn.k_proj",
"model.layers.28.self_attn.o_norm",
"model.layers.28.self_attn.o_proj",
"model.layers.28.self_attn.q_conv1d",
"model.layers.28.self_attn.q_proj",
"model.layers.28.self_attn.qkv_proj",
"model.layers.28.self_attn.v_conv1d",
"model.layers.28.self_attn.v_proj",
"model.layers.29.hc_attn_base",
"model.layers.29.hc_attn_fn",
"model.layers.29.hc_attn_scale",
"model.layers.29.hc_ffn_base",
"model.layers.29.hc_ffn_fn",
"model.layers.29.hc_ffn_scale",
"model.layers.29.input_layernorm",
"model.layers.29.mlp.gate",
"model.layers.29.mlp.gate.e_score_correction_bias",
"model.layers.29.post_attention_layernorm",
"model.layers.29.self_attn.A_log",
"model.layers.29.self_attn.b_proj",
"model.layers.29.self_attn.dt_bias",
"model.layers.29.self_attn.f_a_proj",
"model.layers.29.self_attn.f_b_proj",
"model.layers.29.self_attn.fused_qkvbfg_a_proj",
"model.layers.29.self_attn.g_a_proj",
"model.layers.29.self_attn.g_b_proj",
"model.layers.29.self_attn.k_conv1d",
"model.layers.29.self_attn.k_proj",
"model.layers.29.self_attn.o_norm",
"model.layers.29.self_attn.o_proj",
"model.layers.29.self_attn.q_conv1d",
"model.layers.29.self_attn.q_proj",
"model.layers.29.self_attn.qkv_proj",
"model.layers.29.self_attn.v_conv1d",
"model.layers.29.self_attn.v_proj",
"model.layers.3.hc_attn_base",
"model.layers.3.hc_attn_fn",
"model.layers.3.hc_attn_scale",
"model.layers.3.hc_ffn_base",
"model.layers.3.hc_ffn_fn",
"model.layers.3.hc_ffn_scale",
"model.layers.3.input_layernorm",
"model.layers.3.mlp.gate",
"model.layers.3.mlp.gate.e_score_correction_bias",
"model.layers.3.post_attention_layernorm",
"model.layers.3.self_attn.indexer.index_kpool_compress_ape",
"model.layers.3.self_attn.indexer.index_kpool_compress_gate",
"model.layers.3.self_attn.indexer.k_norm",
"model.layers.3.self_attn.indexer.k_norm.bias",
"model.layers.3.self_attn.indexer.weights_proj",
"model.layers.3.self_attn.indexer.wk",
"model.layers.3.self_attn.indexer.wq_b",
"model.layers.3.self_attn.kv_a_layernorm",
"model.layers.3.self_attn.kv_b_proj",
"model.layers.3.self_attn.q_a_layernorm",
"model.layers.30.hc_attn_base",
"model.layers.30.hc_attn_fn",
"model.layers.30.hc_attn_scale",
"model.layers.30.hc_ffn_base",
"model.layers.30.hc_ffn_fn",
"model.layers.30.hc_ffn_scale",
"model.layers.30.input_layernorm",
"model.layers.30.mlp.gate",
"model.layers.30.mlp.gate.e_score_correction_bias",
"model.layers.30.post_attention_layernorm",
"model.layers.30.self_attn.A_log",
"model.layers.30.self_attn.b_proj",
"model.layers.30.self_attn.dt_bias",
"model.layers.30.self_attn.f_a_proj",
"model.layers.30.self_attn.f_b_proj",
"model.layers.30.self_attn.fused_qkvbfg_a_proj",
"model.layers.30.self_attn.g_a_proj",
"model.layers.30.self_attn.g_b_proj",
"model.layers.30.self_attn.k_conv1d",
"model.layers.30.self_attn.k_proj",
"model.layers.30.self_attn.o_norm",
"model.layers.30.self_attn.o_proj",
"model.layers.30.self_attn.q_conv1d",
"model.layers.30.self_attn.q_proj",
"model.layers.30.self_attn.qkv_proj",
"model.layers.30.self_attn.v_conv1d",
"model.layers.30.self_attn.v_proj",
"model.layers.31.hc_attn_base",
"model.layers.31.hc_attn_fn",
"model.layers.31.hc_attn_scale",
"model.layers.31.hc_ffn_base",
"model.layers.31.hc_ffn_fn",
"model.layers.31.hc_ffn_scale",
"model.layers.31.input_layernorm",
"model.layers.31.mlp.gate",
"model.layers.31.mlp.gate.e_score_correction_bias",
"model.layers.31.post_attention_layernorm",
"model.layers.31.self_attn.indexer.index_kpool_compress_ape",
"model.layers.31.self_attn.indexer.index_kpool_compress_gate",
"model.layers.31.self_attn.indexer.k_norm",
"model.layers.31.self_attn.indexer.k_norm.bias",
"model.layers.31.self_attn.indexer.weights_proj",
"model.layers.31.self_attn.indexer.wk",
"model.layers.31.self_attn.indexer.wq_b",
"model.layers.31.self_attn.kv_a_layernorm",
"model.layers.31.self_attn.kv_b_proj",
"model.layers.31.self_attn.q_a_layernorm",
"model.layers.32.hc_attn_base",
"model.layers.32.hc_attn_fn",
"model.layers.32.hc_attn_scale",
"model.layers.32.hc_ffn_base",
"model.layers.32.hc_ffn_fn",
"model.layers.32.hc_ffn_scale",
"model.layers.32.input_layernorm",
"model.layers.32.mlp.gate",
"model.layers.32.mlp.gate.e_score_correction_bias",
"model.layers.32.post_attention_layernorm",
"model.layers.32.self_attn.A_log",
"model.layers.32.self_attn.b_proj",
"model.layers.32.self_attn.dt_bias",
"model.layers.32.self_attn.f_a_proj",
"model.layers.32.self_attn.f_b_proj",
"model.layers.32.self_attn.fused_qkvbfg_a_proj",
"model.layers.32.self_attn.g_a_proj",
"model.layers.32.self_attn.g_b_proj",
"model.layers.32.self_attn.k_conv1d",
"model.layers.32.self_attn.k_proj",
"model.layers.32.self_attn.o_norm",
"model.layers.32.self_attn.o_proj",
"model.layers.32.self_attn.q_conv1d",
"model.layers.32.self_attn.q_proj",
"model.layers.32.self_attn.qkv_proj",
"model.layers.32.self_attn.v_conv1d",
"model.layers.32.self_attn.v_proj",
"model.layers.33.hc_attn_base",
"model.layers.33.hc_attn_fn",
"model.layers.33.hc_attn_scale",
"model.layers.33.hc_ffn_base",
"model.layers.33.hc_ffn_fn",
"model.layers.33.hc_ffn_scale",
"model.layers.33.input_layernorm",
"model.layers.33.mlp.gate",
"model.layers.33.mlp.gate.e_score_correction_bias",
"model.layers.33.post_attention_layernorm",
"model.layers.33.self_attn.A_log",
"model.layers.33.self_attn.b_proj",
"model.layers.33.self_attn.dt_bias",
"model.layers.33.self_attn.f_a_proj",
"model.layers.33.self_attn.f_b_proj",
"model.layers.33.self_attn.fused_qkvbfg_a_proj",
"model.layers.33.self_attn.g_a_proj",
"model.layers.33.self_attn.g_b_proj",
"model.layers.33.self_attn.k_conv1d",
"model.layers.33.self_attn.k_proj",
"model.layers.33.self_attn.o_norm",
"model.layers.33.self_attn.o_proj",
"model.layers.33.self_attn.q_conv1d",
"model.layers.33.self_attn.q_proj",
"model.layers.33.self_attn.qkv_proj",
"model.layers.33.self_attn.v_conv1d",
"model.layers.33.self_attn.v_proj",
"model.layers.34.hc_attn_base",
"model.layers.34.hc_attn_fn",
"model.layers.34.hc_attn_scale",
"model.layers.34.hc_ffn_base",
"model.layers.34.hc_ffn_fn",
"model.layers.34.hc_ffn_scale",
"model.layers.34.input_layernorm",
"model.layers.34.mlp.gate",
"model.layers.34.mlp.gate.e_score_correction_bias",
"model.layers.34.post_attention_layernorm",
"model.layers.34.self_attn.A_log",
"model.layers.34.self_attn.b_proj",
"model.layers.34.self_attn.dt_bias",
"model.layers.34.self_attn.f_a_proj",
"model.layers.34.self_attn.f_b_proj",
"model.layers.34.self_attn.fused_qkvbfg_a_proj",
"model.layers.34.self_attn.g_a_proj",
"model.layers.34.self_attn.g_b_proj",
"model.layers.34.self_attn.k_conv1d",
"model.layers.34.self_attn.k_proj",
"model.layers.34.self_attn.o_norm",
"model.layers.34.self_attn.o_proj",
"model.layers.34.self_attn.q_conv1d",
"model.layers.34.self_attn.q_proj",
"model.layers.34.self_attn.qkv_proj",
"model.layers.34.self_attn.v_conv1d",
"model.layers.34.self_attn.v_proj",
"model.layers.35.hc_attn_base",
"model.layers.35.hc_attn_fn",
"model.layers.35.hc_attn_scale",
"model.layers.35.hc_ffn_base",
"model.layers.35.hc_ffn_fn",
"model.layers.35.hc_ffn_scale",
"model.layers.35.input_layernorm",
"model.layers.35.mlp.gate",
"model.layers.35.mlp.gate.e_score_correction_bias",
"model.layers.35.post_attention_layernorm",
"model.layers.35.self_attn.indexer.index_kpool_compress_ape",
"model.layers.35.self_attn.indexer.index_kpool_compress_gate",
"model.layers.35.self_attn.indexer.k_norm",
"model.layers.35.self_attn.indexer.k_norm.bias",
"model.layers.35.self_attn.indexer.weights_proj",
"model.layers.35.self_attn.indexer.wk",
"model.layers.35.self_attn.indexer.wq_b",
"model.layers.35.self_attn.kv_a_layernorm",
"model.layers.35.self_attn.kv_b_proj",
"model.layers.35.self_attn.q_a_layernorm",
"model.layers.36.hc_attn_base",
"model.layers.36.hc_attn_fn",
"model.layers.36.hc_attn_scale",
"model.layers.36.hc_ffn_base",
"model.layers.36.hc_ffn_fn",
"model.layers.36.hc_ffn_scale",
"model.layers.36.input_layernorm",
"model.layers.36.mlp.gate",
"model.layers.36.mlp.gate.e_score_correction_bias",
"model.layers.36.post_attention_layernorm",
"model.layers.36.self_attn.A_log",
"model.layers.36.self_attn.b_proj",
"model.layers.36.self_attn.dt_bias",
"model.layers.36.self_attn.f_a_proj",
"model.layers.36.self_attn.f_b_proj",
"model.layers.36.self_attn.fused_qkvbfg_a_proj",
"model.layers.36.self_attn.g_a_proj",
"model.layers.36.self_attn.g_b_proj",
"model.layers.36.self_attn.k_conv1d",
"model.layers.36.self_attn.k_proj",
"model.layers.36.self_attn.o_norm",
"model.layers.36.self_attn.o_proj",
"model.layers.36.self_attn.q_conv1d",
"model.layers.36.self_attn.q_proj",
"model.layers.36.self_attn.qkv_proj",
"model.layers.36.self_attn.v_conv1d",
"model.layers.36.self_attn.v_proj",
"model.layers.37.hc_attn_base",
"model.layers.37.hc_attn_fn",
"model.layers.37.hc_attn_scale",
"model.layers.37.hc_ffn_base",
"model.layers.37.hc_ffn_fn",
"model.layers.37.hc_ffn_scale",
"model.layers.37.input_layernorm",
"model.layers.37.mlp.gate",
"model.layers.37.mlp.gate.e_score_correction_bias",
"model.layers.37.post_attention_layernorm",
"model.layers.37.self_attn.A_log",
"model.layers.37.self_attn.b_proj",
"model.layers.37.self_attn.dt_bias",
"model.layers.37.self_attn.f_a_proj",
"model.layers.37.self_attn.f_b_proj",
"model.layers.37.self_attn.fused_qkvbfg_a_proj",
"model.layers.37.self_attn.g_a_proj",
"model.layers.37.self_attn.g_b_proj",
"model.layers.37.self_attn.k_conv1d",
"model.layers.37.self_attn.k_proj",
"model.layers.37.self_attn.o_norm",
"model.layers.37.self_attn.o_proj",
"model.layers.37.self_attn.q_conv1d",
"model.layers.37.self_attn.q_proj",
"model.layers.37.self_attn.qkv_proj",
"model.layers.37.self_attn.v_conv1d",
"model.layers.37.self_attn.v_proj",
"model.layers.38.hc_attn_base",
"model.layers.38.hc_attn_fn",
"model.layers.38.hc_attn_scale",
"model.layers.38.hc_ffn_base",
"model.layers.38.hc_ffn_fn",
"model.layers.38.hc_ffn_scale",
"model.layers.38.input_layernorm",
"model.layers.38.mlp.gate",
"model.layers.38.mlp.gate.e_score_correction_bias",
"model.layers.38.post_attention_layernorm",
"model.layers.38.self_attn.A_log",
"model.layers.38.self_attn.b_proj",
"model.layers.38.self_attn.dt_bias",
"model.layers.38.self_attn.f_a_proj",
"model.layers.38.self_attn.f_b_proj",
"model.layers.38.self_attn.fused_qkvbfg_a_proj",
"model.layers.38.self_attn.g_a_proj",
"model.layers.38.self_attn.g_b_proj",
"model.layers.38.self_attn.k_conv1d",
"model.layers.38.self_attn.k_proj",
"model.layers.38.self_attn.o_norm",
"model.layers.38.self_attn.o_proj",
"model.layers.38.self_attn.q_conv1d",
"model.layers.38.self_attn.q_proj",
"model.layers.38.self_attn.qkv_proj",
"model.layers.38.self_attn.v_conv1d",
"model.layers.38.self_attn.v_proj",
"model.layers.39.hc_attn_base",
"model.layers.39.hc_attn_fn",
"model.layers.39.hc_attn_scale",
"model.layers.39.hc_ffn_base",
"model.layers.39.hc_ffn_fn",
"model.layers.39.hc_ffn_scale",
"model.layers.39.input_layernorm",
"model.layers.39.mlp.gate",
"model.layers.39.mlp.gate.e_score_correction_bias",
"model.layers.39.post_attention_layernorm",
"model.layers.39.self_attn.indexer.index_kpool_compress_ape",
"model.layers.39.self_attn.indexer.index_kpool_compress_gate",
"model.layers.39.self_attn.indexer.k_norm",
"model.layers.39.self_attn.indexer.k_norm.bias",
"model.layers.39.self_attn.indexer.weights_proj",
"model.layers.39.self_attn.indexer.wk",
"model.layers.39.self_attn.indexer.wq_b",
"model.layers.39.self_attn.kv_a_layernorm",
"model.layers.39.self_attn.kv_b_proj",
"model.layers.39.self_attn.q_a_layernorm",
"model.layers.4.hc_attn_base",
"model.layers.4.hc_attn_fn",
"model.layers.4.hc_attn_scale",
"model.layers.4.hc_ffn_base",
"model.layers.4.hc_ffn_fn",
"model.layers.4.hc_ffn_scale",
"model.layers.4.input_layernorm",
"model.layers.4.mlp.gate",
"model.layers.4.mlp.gate.e_score_correction_bias",
"model.layers.4.post_attention_layernorm",
"model.layers.4.self_attn.A_log",
"model.layers.4.self_attn.b_proj",
"model.layers.4.self_attn.dt_bias",
"model.layers.4.self_attn.f_a_proj",
"model.layers.4.self_attn.f_b_proj",
"model.layers.4.self_attn.fused_qkvbfg_a_proj",
"model.layers.4.self_attn.g_a_proj",
"model.layers.4.self_attn.g_b_proj",
"model.layers.4.self_attn.k_conv1d",
"model.layers.4.self_attn.k_proj",
"model.layers.4.self_attn.o_norm",
"model.layers.4.self_attn.o_proj",
"model.layers.4.self_attn.q_conv1d",
"model.layers.4.self_attn.q_proj",
"model.layers.4.self_attn.qkv_proj",
"model.layers.4.self_attn.v_conv1d",
"model.layers.4.self_attn.v_proj",
"model.layers.40.hc_attn_base",
"model.layers.40.hc_attn_fn",
"model.layers.40.hc_attn_scale",
"model.layers.40.hc_ffn_base",
"model.layers.40.hc_ffn_fn",
"model.layers.40.hc_ffn_scale",
"model.layers.40.input_layernorm",
"model.layers.40.mlp.gate",
"model.layers.40.mlp.gate.e_score_correction_bias",
"model.layers.40.post_attention_layernorm",
"model.layers.40.self_attn.A_log",
"model.layers.40.self_attn.b_proj",
"model.layers.40.self_attn.dt_bias",
"model.layers.40.self_attn.f_a_proj",
"model.layers.40.self_attn.f_b_proj",
"model.layers.40.self_attn.fused_qkvbfg_a_proj",
"model.layers.40.self_attn.g_a_proj",
"model.layers.40.self_attn.g_b_proj",
"model.layers.40.self_attn.k_conv1d",
"model.layers.40.self_attn.k_proj",
"model.layers.40.self_attn.o_norm",
"model.layers.40.self_attn.o_proj",
"model.layers.40.self_attn.q_conv1d",
"model.layers.40.self_attn.q_proj",
"model.layers.40.self_attn.qkv_proj",
"model.layers.40.self_attn.v_conv1d",
"model.layers.40.self_attn.v_proj",
"model.layers.41.hc_attn_base",
"model.layers.41.hc_attn_fn",
"model.layers.41.hc_attn_scale",
"model.layers.41.hc_ffn_base",
"model.layers.41.hc_ffn_fn",
"model.layers.41.hc_ffn_scale",
"model.layers.41.input_layernorm",
"model.layers.41.mlp.gate",
"model.layers.41.mlp.gate.e_score_correction_bias",
"model.layers.41.post_attention_layernorm",
"model.layers.41.self_attn.A_log",
"model.layers.41.self_attn.b_proj",
"model.layers.41.self_attn.dt_bias",
"model.layers.41.self_attn.f_a_proj",
"model.layers.41.self_attn.f_b_proj",
"model.layers.41.self_attn.fused_qkvbfg_a_proj",
"model.layers.41.self_attn.g_a_proj",
"model.layers.41.self_attn.g_b_proj",
"model.layers.41.self_attn.k_conv1d",
"model.layers.41.self_attn.k_proj",
"model.layers.41.self_attn.o_norm",
"model.layers.41.self_attn.o_proj",
"model.layers.41.self_attn.q_conv1d",
"model.layers.41.self_attn.q_proj",
"model.layers.41.self_attn.qkv_proj",
"model.layers.41.self_attn.v_conv1d",
"model.layers.41.self_attn.v_proj",
"model.layers.42.hc_attn_base",
"model.layers.42.hc_attn_fn",
"model.layers.42.hc_attn_scale",
"model.layers.42.hc_ffn_base",
"model.layers.42.hc_ffn_fn",
"model.layers.42.hc_ffn_scale",
"model.layers.42.input_layernorm",
"model.layers.42.mlp.gate",
"model.layers.42.mlp.gate.e_score_correction_bias",
"model.layers.42.post_attention_layernorm",
"model.layers.42.self_attn.A_log",
"model.layers.42.self_attn.b_proj",
"model.layers.42.self_attn.dt_bias",
"model.layers.42.self_attn.f_a_proj",
"model.layers.42.self_attn.f_b_proj",
"model.layers.42.self_attn.fused_qkvbfg_a_proj",
"model.layers.42.self_attn.g_a_proj",
"model.layers.42.self_attn.g_b_proj",
"model.layers.42.self_attn.k_conv1d",
"model.layers.42.self_attn.k_proj",
"model.layers.42.self_attn.o_norm",
"model.layers.42.self_attn.o_proj",
"model.layers.42.self_attn.q_conv1d",
"model.layers.42.self_attn.q_proj",
"model.layers.42.self_attn.qkv_proj",
"model.layers.42.self_attn.v_conv1d",
"model.layers.42.self_attn.v_proj",
"model.layers.43.hc_attn_base",
"model.layers.43.hc_attn_fn",
"model.layers.43.hc_attn_scale",
"model.layers.43.hc_ffn_base",
"model.layers.43.hc_ffn_fn",
"model.layers.43.hc_ffn_scale",
"model.layers.43.input_layernorm",
"model.layers.43.mlp.gate",
"model.layers.43.mlp.gate.e_score_correction_bias",
"model.layers.43.post_attention_layernorm",
"model.layers.43.self_attn.indexer.index_kpool_compress_ape",
"model.layers.43.self_attn.indexer.index_kpool_compress_gate",
"model.layers.43.self_attn.indexer.k_norm",
"model.layers.43.self_attn.indexer.k_norm.bias",
"model.layers.43.self_attn.indexer.weights_proj",
"model.layers.43.self_attn.indexer.wk",
"model.layers.43.self_attn.indexer.wq_b",
"model.layers.43.self_attn.kv_a_layernorm",
"model.layers.43.self_attn.kv_b_proj",
"model.layers.43.self_attn.q_a_layernorm",
"model.layers.44.hc_attn_base",
"model.layers.44.hc_attn_fn",
"model.layers.44.hc_attn_scale",
"model.layers.44.hc_ffn_base",
"model.layers.44.hc_ffn_fn",
"model.layers.44.hc_ffn_scale",
"model.layers.44.input_layernorm",
"model.layers.44.mlp.gate",
"model.layers.44.mlp.gate.e_score_correction_bias",
"model.layers.44.post_attention_layernorm",
"model.layers.44.self_attn.A_log",
"model.layers.44.self_attn.b_proj",
"model.layers.44.self_attn.dt_bias",
"model.layers.44.self_attn.f_a_proj",
"model.layers.44.self_attn.f_b_proj",
"model.layers.44.self_attn.fused_qkvbfg_a_proj",
"model.layers.44.self_attn.g_a_proj",
"model.layers.44.self_attn.g_b_proj",
"model.layers.44.self_attn.k_conv1d",
"model.layers.44.self_attn.k_proj",
"model.layers.44.self_attn.o_norm",
"model.layers.44.self_attn.o_proj",
"model.layers.44.self_attn.q_conv1d",
"model.layers.44.self_attn.q_proj",
"model.layers.44.self_attn.qkv_proj",
"model.layers.44.self_attn.v_conv1d",
"model.layers.44.self_attn.v_proj",
"model.layers.45.eh_proj",
"model.layers.45.enorm",
"model.layers.45.hnorm",
"model.layers.45.input_layernorm",
"model.layers.45.mlp.gate",
"model.layers.45.mlp.gate.e_score_correction_bias",
"model.layers.45.post_attention_layernorm",
"model.layers.45.self_attn.indexer.index_kpool_compress_ape",
"model.layers.45.self_attn.indexer.index_kpool_compress_gate",
"model.layers.45.self_attn.indexer.k_norm",
"model.layers.45.self_attn.indexer.k_norm.bias",
"model.layers.45.self_attn.indexer.weights_proj",
"model.layers.45.self_attn.indexer.wk",
"model.layers.45.self_attn.indexer.wq_b",
"model.layers.45.self_attn.kv_a_layernorm",
"model.layers.45.self_attn.kv_b_proj",
"model.layers.45.self_attn.q_a_layernorm",
"model.layers.45.shared_head.norm",
"model.layers.5.hc_attn_base",
"model.layers.5.hc_attn_fn",
"model.layers.5.hc_attn_scale",
"model.layers.5.hc_ffn_base",
"model.layers.5.hc_ffn_fn",
"model.layers.5.hc_ffn_scale",
"model.layers.5.input_layernorm",
"model.layers.5.mlp.gate",
"model.layers.5.mlp.gate.e_score_correction_bias",
"model.layers.5.post_attention_layernorm",
"model.layers.5.self_attn.A_log",
"model.layers.5.self_attn.b_proj",
"model.layers.5.self_attn.dt_bias",
"model.layers.5.self_attn.f_a_proj",
"model.layers.5.self_attn.f_b_proj",
"model.layers.5.self_attn.fused_qkvbfg_a_proj",
"model.layers.5.self_attn.g_a_proj",
"model.layers.5.self_attn.g_b_proj",
"model.layers.5.self_attn.k_conv1d",
"model.layers.5.self_attn.k_proj",
"model.layers.5.self_attn.o_norm",
"model.layers.5.self_attn.o_proj",
"model.layers.5.self_attn.q_conv1d",
"model.layers.5.self_attn.q_proj",
"model.layers.5.self_attn.qkv_proj",
"model.layers.5.self_attn.v_conv1d",
"model.layers.5.self_attn.v_proj",
"model.layers.6.hc_attn_base",
"model.layers.6.hc_attn_fn",
"model.layers.6.hc_attn_scale",
"model.layers.6.hc_ffn_base",
"model.layers.6.hc_ffn_fn",
"model.layers.6.hc_ffn_scale",
"model.layers.6.input_layernorm",
"model.layers.6.mlp.gate",
"model.layers.6.mlp.gate.e_score_correction_bias",
"model.layers.6.post_attention_layernorm",
"model.layers.6.self_attn.A_log",
"model.layers.6.self_attn.b_proj",
"model.layers.6.self_attn.dt_bias",
"model.layers.6.self_attn.f_a_proj",
"model.layers.6.self_attn.f_b_proj",
"model.layers.6.self_attn.fused_qkvbfg_a_proj",
"model.layers.6.self_attn.g_a_proj",
"model.layers.6.self_attn.g_b_proj",
"model.layers.6.self_attn.k_conv1d",
"model.layers.6.self_attn.k_proj",
"model.layers.6.self_attn.o_norm",
"model.layers.6.self_attn.o_proj",
"model.layers.6.self_attn.q_conv1d",
"model.layers.6.self_attn.q_proj",
"model.layers.6.self_attn.qkv_proj",
"model.layers.6.self_attn.v_conv1d",
"model.layers.6.self_attn.v_proj",
"model.layers.7.hc_attn_base",
"model.layers.7.hc_attn_fn",
"model.layers.7.hc_attn_scale",
"model.layers.7.hc_ffn_base",
"model.layers.7.hc_ffn_fn",
"model.layers.7.hc_ffn_scale",
"model.layers.7.input_layernorm",
"model.layers.7.mlp.gate",
"model.layers.7.mlp.gate.e_score_correction_bias",
"model.layers.7.post_attention_layernorm",
"model.layers.7.self_attn.indexer.index_kpool_compress_ape",
"model.layers.7.self_attn.indexer.index_kpool_compress_gate",
"model.layers.7.self_attn.indexer.k_norm",
"model.layers.7.self_attn.indexer.k_norm.bias",
"model.layers.7.self_attn.indexer.weights_proj",
"model.layers.7.self_attn.indexer.wk",
"model.layers.7.self_attn.indexer.wq_b",
"model.layers.7.self_attn.kv_a_layernorm",
"model.layers.7.self_attn.kv_b_proj",
"model.layers.7.self_attn.q_a_layernorm",
"model.layers.8.hc_attn_base",
"model.layers.8.hc_attn_fn",
"model.layers.8.hc_attn_scale",
"model.layers.8.hc_ffn_base",
"model.layers.8.hc_ffn_fn",
"model.layers.8.hc_ffn_scale",
"model.layers.8.input_layernorm",
"model.layers.8.mlp.gate",
"model.layers.8.mlp.gate.e_score_correction_bias",
"model.layers.8.post_attention_layernorm",
"model.layers.8.self_attn.A_log",
"model.layers.8.self_attn.b_proj",
"model.layers.8.self_attn.dt_bias",
"model.layers.8.self_attn.f_a_proj",
"model.layers.8.self_attn.f_b_proj",
"model.layers.8.self_attn.fused_qkvbfg_a_proj",
"model.layers.8.self_attn.g_a_proj",
"model.layers.8.self_attn.g_b_proj",
"model.layers.8.self_attn.k_conv1d",
"model.layers.8.self_attn.k_proj",
"model.layers.8.self_attn.o_norm",
"model.layers.8.self_attn.o_proj",
"model.layers.8.self_attn.q_conv1d",
"model.layers.8.self_attn.q_proj",
"model.layers.8.self_attn.qkv_proj",
"model.layers.8.self_attn.v_conv1d",
"model.layers.8.self_attn.v_proj",
"model.layers.9.hc_attn_base",
"model.layers.9.hc_attn_fn",
"model.layers.9.hc_attn_scale",
"model.layers.9.hc_ffn_base",
"model.layers.9.hc_ffn_fn",
"model.layers.9.hc_ffn_scale",
"model.layers.9.input_layernorm",
"model.layers.9.mlp.gate",
"model.layers.9.mlp.gate.e_score_correction_bias",
"model.layers.9.post_attention_layernorm",
"model.layers.9.self_attn.A_log",
"model.layers.9.self_attn.b_proj",
"model.layers.9.self_attn.dt_bias",
"model.layers.9.self_attn.f_a_proj",
"model.layers.9.self_attn.f_b_proj",
"model.layers.9.self_attn.fused_qkvbfg_a_proj",
"model.layers.9.self_attn.g_a_proj",
"model.layers.9.self_attn.g_b_proj",
"model.layers.9.self_attn.k_conv1d",
"model.layers.9.self_attn.k_proj",
"model.layers.9.self_attn.o_norm",
"model.layers.9.self_attn.o_proj",
"model.layers.9.self_attn.q_conv1d",
"model.layers.9.self_attn.q_proj",
"model.layers.9.self_attn.qkv_proj",
"model.layers.9.self_attn.v_conv1d",
"model.layers.9.self_attn.v_proj",
"model.norm",
"model.visual",
"router",
"visual",
"visual.blocks.0.attn.k_norm",
"visual.blocks.0.attn.proj",
"visual.blocks.0.attn.proj.bias",
"visual.blocks.0.attn.q_norm",
"visual.blocks.0.attn.qkv",
"visual.blocks.0.attn.qkv.bias",
"visual.blocks.0.mlp.down_proj",
"visual.blocks.0.mlp.down_proj.bias",
"visual.blocks.0.mlp.gate_proj",
"visual.blocks.0.mlp.gate_proj.bias",
"visual.blocks.0.mlp.up_proj",
"visual.blocks.0.mlp.up_proj.bias",
"visual.blocks.0.norm1",
"visual.blocks.0.norm2",
"visual.blocks.1.attn.k_norm",
"visual.blocks.1.attn.proj",
"visual.blocks.1.attn.proj.bias",
"visual.blocks.1.attn.q_norm",
"visual.blocks.1.attn.qkv",
"visual.blocks.1.attn.qkv.bias",
"visual.blocks.1.mlp.down_proj",
"visual.blocks.1.mlp.down_proj.bias",
"visual.blocks.1.mlp.gate_proj",
"visual.blocks.1.mlp.gate_proj.bias",
"visual.blocks.1.mlp.up_proj",
"visual.blocks.1.mlp.up_proj.bias",
"visual.blocks.1.norm1",
"visual.blocks.1.norm2",
"visual.blocks.10.attn.k_norm",
"visual.blocks.10.attn.proj",
"visual.blocks.10.attn.proj.bias",
"visual.blocks.10.attn.q_norm",
"visual.blocks.10.attn.qkv",
"visual.blocks.10.attn.qkv.bias",
"visual.blocks.10.mlp.down_proj",
"visual.blocks.10.mlp.down_proj.bias",
"visual.blocks.10.mlp.gate_proj",
"visual.blocks.10.mlp.gate_proj.bias",
"visual.blocks.10.mlp.up_proj",
"visual.blocks.10.mlp.up_proj.bias",
"visual.blocks.10.norm1",
"visual.blocks.10.norm2",
"visual.blocks.11.attn.k_norm",
"visual.blocks.11.attn.proj",
"visual.blocks.11.attn.proj.bias",
"visual.blocks.11.attn.q_norm",
"visual.blocks.11.attn.qkv",
"visual.blocks.11.attn.qkv.bias",
"visual.blocks.11.mlp.down_proj",
"visual.blocks.11.mlp.down_proj.bias",
"visual.blocks.11.mlp.gate_proj",
"visual.blocks.11.mlp.gate_proj.bias",
"visual.blocks.11.mlp.up_proj",
"visual.blocks.11.mlp.up_proj.bias",
"visual.blocks.11.norm1",
"visual.blocks.11.norm2",
"visual.blocks.12.attn.k_norm",
"visual.blocks.12.attn.proj",
"visual.blocks.12.attn.proj.bias",
"visual.blocks.12.attn.q_norm",
"visual.blocks.12.attn.qkv",
"visual.blocks.12.attn.qkv.bias",
"visual.blocks.12.mlp.down_proj",
"visual.blocks.12.mlp.down_proj.bias",
"visual.blocks.12.mlp.gate_proj",
"visual.blocks.12.mlp.gate_proj.bias",
"visual.blocks.12.mlp.up_proj",
"visual.blocks.12.mlp.up_proj.bias",
"visual.blocks.12.norm1",
"visual.blocks.12.norm2",
"visual.blocks.13.attn.k_norm",
"visual.blocks.13.attn.proj",
"visual.blocks.13.attn.proj.bias",
"visual.blocks.13.attn.q_norm",
"visual.blocks.13.attn.qkv",
"visual.blocks.13.attn.qkv.bias",
"visual.blocks.13.mlp.down_proj",
"visual.blocks.13.mlp.down_proj.bias",
"visual.blocks.13.mlp.gate_proj",
"visual.blocks.13.mlp.gate_proj.bias",
"visual.blocks.13.mlp.up_proj",
"visual.blocks.13.mlp.up_proj.bias",
"visual.blocks.13.norm1",
"visual.blocks.13.norm2",
"visual.blocks.14.attn.k_norm",
"visual.blocks.14.attn.proj",
"visual.blocks.14.attn.proj.bias",
"visual.blocks.14.attn.q_norm",
"visual.blocks.14.attn.qkv",
"visual.blocks.14.attn.qkv.bias",
"visual.blocks.14.mlp.down_proj",
"visual.blocks.14.mlp.down_proj.bias",
"visual.blocks.14.mlp.gate_proj",
"visual.blocks.14.mlp.gate_proj.bias",
"visual.blocks.14.mlp.up_proj",
"visual.blocks.14.mlp.up_proj.bias",
"visual.blocks.14.norm1",
"visual.blocks.14.norm2",
"visual.blocks.15.attn.k_norm",
"visual.blocks.15.attn.proj",
"visual.blocks.15.attn.proj.bias",
"visual.blocks.15.attn.q_norm",
"visual.blocks.15.attn.qkv",
"visual.blocks.15.attn.qkv.bias",
"visual.blocks.15.mlp.down_proj",
"visual.blocks.15.mlp.down_proj.bias",
"visual.blocks.15.mlp.gate_proj",
"visual.blocks.15.mlp.gate_proj.bias",
"visual.blocks.15.mlp.up_proj",
"visual.blocks.15.mlp.up_proj.bias",
"visual.blocks.15.norm1",
"visual.blocks.15.norm2",
"visual.blocks.16.attn.k_norm",
"visual.blocks.16.attn.proj",
"visual.blocks.16.attn.proj.bias",
"visual.blocks.16.attn.q_norm",
"visual.blocks.16.attn.qkv",
"visual.blocks.16.attn.qkv.bias",
"visual.blocks.16.mlp.down_proj",
"visual.blocks.16.mlp.down_proj.bias",
"visual.blocks.16.mlp.gate_proj",
"visual.blocks.16.mlp.gate_proj.bias",
"visual.blocks.16.mlp.up_proj",
"visual.blocks.16.mlp.up_proj.bias",
"visual.blocks.16.norm1",
"visual.blocks.16.norm2",
"visual.blocks.17.attn.k_norm",
"visual.blocks.17.attn.proj",
"visual.blocks.17.attn.proj.bias",
"visual.blocks.17.attn.q_norm",
"visual.blocks.17.attn.qkv",
"visual.blocks.17.attn.qkv.bias",
"visual.blocks.17.mlp.down_proj",
"visual.blocks.17.mlp.down_proj.bias",
"visual.blocks.17.mlp.gate_proj",
"visual.blocks.17.mlp.gate_proj.bias",
"visual.blocks.17.mlp.up_proj",
"visual.blocks.17.mlp.up_proj.bias",
"visual.blocks.17.norm1",
"visual.blocks.17.norm2",
"visual.blocks.18.attn.k_norm",
"visual.blocks.18.attn.proj",
"visual.blocks.18.attn.proj.bias",
"visual.blocks.18.attn.q_norm",
"visual.blocks.18.attn.qkv",
"visual.blocks.18.attn.qkv.bias",
"visual.blocks.18.mlp.down_proj",
"visual.blocks.18.mlp.down_proj.bias",
"visual.blocks.18.mlp.gate_proj",
"visual.blocks.18.mlp.gate_proj.bias",
"visual.blocks.18.mlp.up_proj",
"visual.blocks.18.mlp.up_proj.bias",
"visual.blocks.18.norm1",
"visual.blocks.18.norm2",
"visual.blocks.19.attn.k_norm",
"visual.blocks.19.attn.proj",
"visual.blocks.19.attn.proj.bias",
"visual.blocks.19.attn.q_norm",
"visual.blocks.19.attn.qkv",
"visual.blocks.19.attn.qkv.bias",
"visual.blocks.19.mlp.down_proj",
"visual.blocks.19.mlp.down_proj.bias",
"visual.blocks.19.mlp.gate_proj",
"visual.blocks.19.mlp.gate_proj.bias",
"visual.blocks.19.mlp.up_proj",
"visual.blocks.19.mlp.up_proj.bias",
"visual.blocks.19.norm1",
"visual.blocks.19.norm2",
"visual.blocks.2.attn.k_norm",
"visual.blocks.2.attn.proj",
"visual.blocks.2.attn.proj.bias",
"visual.blocks.2.attn.q_norm",
"visual.blocks.2.attn.qkv",
"visual.blocks.2.attn.qkv.bias",
"visual.blocks.2.mlp.down_proj",
"visual.blocks.2.mlp.down_proj.bias",
"visual.blocks.2.mlp.gate_proj",
"visual.blocks.2.mlp.gate_proj.bias",
"visual.blocks.2.mlp.up_proj",
"visual.blocks.2.mlp.up_proj.bias",
"visual.blocks.2.norm1",
"visual.blocks.2.norm2",
"visual.blocks.20.attn.k_norm",
"visual.blocks.20.attn.proj",
"visual.blocks.20.attn.proj.bias",
"visual.blocks.20.attn.q_norm",
"visual.blocks.20.attn.qkv",
"visual.blocks.20.attn.qkv.bias",
"visual.blocks.20.mlp.down_proj",
"visual.blocks.20.mlp.down_proj.bias",
"visual.blocks.20.mlp.gate_proj",
"visual.blocks.20.mlp.gate_proj.bias",
"visual.blocks.20.mlp.up_proj",
"visual.blocks.20.mlp.up_proj.bias",
"visual.blocks.20.norm1",
"visual.blocks.20.norm2",
"visual.blocks.21.attn.k_norm",
"visual.blocks.21.attn.proj",
"visual.blocks.21.attn.proj.bias",
"visual.blocks.21.attn.q_norm",
"visual.blocks.21.attn.qkv",
"visual.blocks.21.attn.qkv.bias",
"visual.blocks.21.mlp.down_proj",
"visual.blocks.21.mlp.down_proj.bias",
"visual.blocks.21.mlp.gate_proj",
"visual.blocks.21.mlp.gate_proj.bias",
"visual.blocks.21.mlp.up_proj",
"visual.blocks.21.mlp.up_proj.bias",
"visual.blocks.21.norm1",
"visual.blocks.21.norm2",
"visual.blocks.22.attn.k_norm",
"visual.blocks.22.attn.proj",
"visual.blocks.22.attn.proj.bias",
"visual.blocks.22.attn.q_norm",
"visual.blocks.22.attn.qkv",
"visual.blocks.22.attn.qkv.bias",
"visual.blocks.22.mlp.down_proj",
"visual.blocks.22.mlp.down_proj.bias",
"visual.blocks.22.mlp.gate_proj",
"visual.blocks.22.mlp.gate_proj.bias",
"visual.blocks.22.mlp.up_proj",
"visual.blocks.22.mlp.up_proj.bias",
"visual.blocks.22.norm1",
"visual.blocks.22.norm2",
"visual.blocks.23.attn.k_norm",
"visual.blocks.23.attn.proj",
"visual.blocks.23.attn.proj.bias",
"visual.blocks.23.attn.q_norm",
"visual.blocks.23.attn.qkv",
"visual.blocks.23.attn.qkv.bias",
"visual.blocks.23.mlp.down_proj",
"visual.blocks.23.mlp.down_proj.bias",
"visual.blocks.23.mlp.gate_proj",
"visual.blocks.23.mlp.gate_proj.bias",
"visual.blocks.23.mlp.up_proj",
"visual.blocks.23.mlp.up_proj.bias",
"visual.blocks.23.norm1",
"visual.blocks.23.norm2",
"visual.blocks.3.attn.k_norm",
"visual.blocks.3.attn.proj",
"visual.blocks.3.attn.proj.bias",
"visual.blocks.3.attn.q_norm",
"visual.blocks.3.attn.qkv",
"visual.blocks.3.attn.qkv.bias",
"visual.blocks.3.mlp.down_proj",
"visual.blocks.3.mlp.down_proj.bias",
"visual.blocks.3.mlp.gate_proj",
"visual.blocks.3.mlp.gate_proj.bias",
"visual.blocks.3.mlp.up_proj",
"visual.blocks.3.mlp.up_proj.bias",
"visual.blocks.3.norm1",
"visual.blocks.3.norm2",
"visual.blocks.4.attn.k_norm",
"visual.blocks.4.attn.proj",
"visual.blocks.4.attn.proj.bias",
"visual.blocks.4.attn.q_norm",
"visual.blocks.4.attn.qkv",
"visual.blocks.4.attn.qkv.bias",
"visual.blocks.4.mlp.down_proj",
"visual.blocks.4.mlp.down_proj.bias",
"visual.blocks.4.mlp.gate_proj",
"visual.blocks.4.mlp.gate_proj.bias",
"visual.blocks.4.mlp.up_proj",
"visual.blocks.4.mlp.up_proj.bias",
"visual.blocks.4.norm1",
"visual.blocks.4.norm2",
"visual.blocks.5.attn.k_norm",
"visual.blocks.5.attn.proj",
"visual.blocks.5.attn.proj.bias",
"visual.blocks.5.attn.q_norm",
"visual.blocks.5.attn.qkv",
"visual.blocks.5.attn.qkv.bias",
"visual.blocks.5.mlp.down_proj",
"visual.blocks.5.mlp.down_proj.bias",
"visual.blocks.5.mlp.gate_proj",
"visual.blocks.5.mlp.gate_proj.bias",
"visual.blocks.5.mlp.up_proj",
"visual.blocks.5.mlp.up_proj.bias",
"visual.blocks.5.norm1",
"visual.blocks.5.norm2",
"visual.blocks.6.attn.k_norm",
"visual.blocks.6.attn.proj",
"visual.blocks.6.attn.proj.bias",
"visual.blocks.6.attn.q_norm",
"visual.blocks.6.attn.qkv",
"visual.blocks.6.attn.qkv.bias",
"visual.blocks.6.mlp.down_proj",
"visual.blocks.6.mlp.down_proj.bias",
"visual.blocks.6.mlp.gate_proj",
"visual.blocks.6.mlp.gate_proj.bias",
"visual.blocks.6.mlp.up_proj",
"visual.blocks.6.mlp.up_proj.bias",
"visual.blocks.6.norm1",
"visual.blocks.6.norm2",
"visual.blocks.7.attn.k_norm",
"visual.blocks.7.attn.proj",
"visual.blocks.7.attn.proj.bias",
"visual.blocks.7.attn.q_norm",
"visual.blocks.7.attn.qkv",
"visual.blocks.7.attn.qkv.bias",
"visual.blocks.7.mlp.down_proj",
"visual.blocks.7.mlp.down_proj.bias",
"visual.blocks.7.mlp.gate_proj",
"visual.blocks.7.mlp.gate_proj.bias",
"visual.blocks.7.mlp.up_proj",
"visual.blocks.7.mlp.up_proj.bias",
"visual.blocks.7.norm1",
"visual.blocks.7.norm2",
"visual.blocks.8.attn.k_norm",
"visual.blocks.8.attn.proj",
"visual.blocks.8.attn.proj.bias",
"visual.blocks.8.attn.q_norm",
"visual.blocks.8.attn.qkv",
"visual.blocks.8.attn.qkv.bias",
"visual.blocks.8.mlp.down_proj",
"visual.blocks.8.mlp.down_proj.bias",
"visual.blocks.8.mlp.gate_proj",
"visual.blocks.8.mlp.gate_proj.bias",
"visual.blocks.8.mlp.up_proj",
"visual.blocks.8.mlp.up_proj.bias",
"visual.blocks.8.norm1",
"visual.blocks.8.norm2",
"visual.blocks.9.attn.k_norm",
"visual.blocks.9.attn.proj",
"visual.blocks.9.attn.proj.bias",
"visual.blocks.9.attn.q_norm",
"visual.blocks.9.attn.qkv",
"visual.blocks.9.attn.qkv.bias",
"visual.blocks.9.mlp.down_proj",
"visual.blocks.9.mlp.down_proj.bias",
"visual.blocks.9.mlp.gate_proj",
"visual.blocks.9.mlp.gate_proj.bias",
"visual.blocks.9.mlp.up_proj",
"visual.blocks.9.mlp.up_proj.bias",
"visual.blocks.9.norm1",
"visual.blocks.9.norm2",
"visual.downsample",
"visual.downsample.bias",
"visual.merger.down_proj",
"visual.merger.gate_proj",
"visual.merger.post_projection_norm",
"visual.merger.post_projection_norm.bias",
"visual.merger.proj",
"visual.merger.up_proj",
"visual.patch_embed.proj",
"visual.patch_embed.proj.bias",
"visual.post_layernorm",
"weights_proj"
],
"quant_method": "fp8"
},
"tokenizer_config": {
"eos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>"
}
},
"createdAt": "2026-08-26T21:09:20.000Z",
"disabled": false,
"downloads": 49224,
"gated": false,
"id": "dealignai/GLM-5.3-Flash-UNCENSORED-FP8",
"lastModified": "2026-09-19T16:32:29.000Z",
"likes": 126,
"model-index": null,
"modelId": "dealignai/GLM-5.3-Flash-UNCENSORED-FP8",
"private": false,
"safetensors": {
"parameters": {
"BF16": 6926096640,
"F32": 295518,
"F8_E4M3": 314396639232
},
"total": 321323031390
},
"sha": "d5822b068da8ddb301665b48c58718e6e18a2c3a",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "dealign_logo.png"
},
{
"rfilename": "dealign_mascot.png"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "model-00001-of-00062.safetensors"
},
{
"rfilename": "model-00002-of-00062.safetensors"
},
{
"rfilename": "model-00003-of-00062.safetensors"
},
{
"rfilename": "model-00004-of-00062.safetensors"
},
{
"rfilename": "model-00005-of-00062.safetensors"
},
{
"rfilename": "model-00006-of-00062.safetensors"
},
{
"rfilename": "model-00007-of-00062.safetensors"
},
{
"rfilename": "model-00008-of-00062.safetensors"
},
{
"rfilename": "model-00009-of-00062.safetensors"
},
{
"rfilename": "model-00010-of-00062.safetensors"
},
{
"rfilename": "model-00011-of-00062.safetensors"
},
{
"rfilename": "model-00012-of-00062.safetensors"
},
{
"rfilename": "model-00013-of-00062.safetensors"
},
{
"rfilename": "model-00014-of-00062.safetensors"
},
{
"rfilename": "model-00015-of-00062.safetensors"
},
{
"rfilename": "model-00016-of-00062.safetensors"
},
{
"rfilename": "model-00017-of-00062.safetensors"
},
{
"rfilename": "model-00018-of-00062.safetensors"
},
{
"rfilename": "model-00019-of-00062.safetensors"
},
{
"rfilename": "model-00020-of-00062.safetensors"
},
{
"rfilename": "model-00021-of-00062.safetensors"
},
{
"rfilename": "model-00022-of-00062.safetensors"
},
{
"rfilename": "model-00023-of-00062.safetensors"
},
{
"rfilename": "model-00024-of-00062.safetensors"
},
{
"rfilename": "model-00025-of-00062.safetensors"
},
{
"rfilename": "model-00026-of-00062.safetensors"
},
{
"rfilename": "model-00027-of-00062.safetensors"
},
{
"rfilename": "model-00028-of-00062.safetensors"
},
{
"rfilename": "model-00029-of-00062.safetensors"
},
{
"rfilename": "model-00030-of-00062.safetensors"
},
{
"rfilename": "model-00031-of-00062.safetensors"
},
{
"rfilename": "model-00032-of-00062.safetensors"
},
{
"rfilename": "model-00033-of-00062.safetensors"
},
{
"rfilename": "model-00034-of-00062.safetensors"
},
{
"rfilename": "model-00035-of-00062.safetensors"
},
{
"rfilename": "model-00036-of-00062.safetensors"
},
{
"rfilename": "model-00037-of-00062.safetensors"
},
{
"rfilename": "model-00038-of-00062.safetensors"
},
{
"rfilename": "model-00039-of-00062.safetensors"
},
{
"rfilename": "model-00040-of-00062.safetensors"
},
{
"rfilename": "model-00041-of-00062.safetensors"
},
{
"rfilename": "model-00042-of-00062.safetensors"
},
{
"rfilename": "model-00043-of-00062.safetensors"
},
{
"rfilename": "model-00044-of-00062.safetensors"
},
{
"rfilename": "model-00045-of-00062.safetensors"
},
{
"rfilename": "model-00046-of-00062.safetensors"
},
{
"rfilename": "model-00047-of-00062.safetensors"
},
{
"rfilename": "model-00048-of-00062.safetensors"
},
{
"rfilename": "model-00049-of-00062.safetensors"
},
{
"rfilename": "model-00050-of-00062.safetensors"
},
{
"rfilename": "model-00051-of-00062.safetensors"
},
{
"rfilename": "model-00052-of-00062.safetensors"
},
{
"rfilename": "model-00053-of-00062.safetensors"
},
{
"rfilename": "model-00054-of-00062.safetensors"
},
{
"rfilename": "model-00055-of-00062.safetensors"
},
{
"rfilename": "model-00056-of-00062.safetensors"
},
{
"rfilename": "model-00057-of-00062.safetensors"
},
{
"rfilename": "model-00058-of-00062.safetensors"
},
{
"rfilename": "model-00059-of-00062.safetensors"
},
{
"rfilename": "model-00060-of-00062.safetensors"
},
{
"rfilename": "model-00061-of-00062.safetensors"
},
{
"rfilename": "model-00062-of-00062.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "processor_config.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
}
],
"spaces": [
"tardellirs/model-pulse",
"aquanode/gpu-vram-calculator"
],
"tags": [
"safetensors",
"glm5_next",
"abliterated",
"uncensored",
"crack",
"glm",
"moe",
"fp8",
"vision",
"mtp",
"en",
"base_model:zai-org/GLM-5.3-Flash",
"base_model:quantized:zai-org/GLM-5.3-Flash",
"license:mit",
"region:us"
],
"usedStorage": 505375369250
} | ||||||||
| gated | falsereceipt
What the source handed over{
"_asked": "dealignai/GLM-5.3-Flash-UNCENSORED-FP8",
"_id": "6a8f5600e8e799f3299d529f",
"author": "dealignai",
"cardData": {
"base_model": [
"zai-org/GLM-5.3-Flash"
],
"language": [
"en"
],
"license": "mit",
"tags": [
"abliterated",
"uncensored",
"crack",
"glm",
"moe",
"fp8",
"vision",
"mtp"
],
"thumbnail": "dealign_mascot.png"
},
"config": {
"architectures": [
"Glm5NextForConditionalGeneration"
],
"chat_template_jinja": "[gMASK]<sop>\n{%- set effective_reasoning_effort = reasoning_effort if reasoning_effort is defined and reasoning_effort in ['low', 'high'] else 'max' -%}\n{%- if effective_reasoning_effort is not none -%}<|system|>Reasoning Effort: {{ effective_reasoning_effort | capitalize }}{%- endif -%}\n{%- set clear_thinking = clear_thinking if clear_thinking is defined else true -%}\n{%- if tools -%}\n{%- macro tool_to_json(tool) -%}\n {%- set ns_tool = namespace(first=true) -%}\n {{ '{' -}}\n {%- for k, v in tool.items() -%}\n {%- if k != 'defer_loading' and k != 'strict' -%}\n {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}\n {%- set ns_tool.first = false -%}\n \"{{ k }}\": {{ v | tojson(ensure_ascii=False) }}\n {%- endif -%}\n {%- endfor -%}\n {{- '}' -}}\n{%- endmacro -%}\n{%- macro tool_references_to_response(refs) -%}\n {{- '<tool_response><tools>\\n' -}}\n {%- for tr in refs -%}\n {%- for tool in tools -%}\n {%- if 'function' in tool -%}\n {%- set tool = tool['function'] -%}\n {%- endif -%}\n {%- if tool.name == tr.name -%}\n {{- tool_to_json(tool) + '\\n' -}}\n {%- endif -%}\n {%- endfor -%}\n {%- endfor -%}\n {{- '</tools></tool_response>' -}}\n{%- endmacro -%}\n<|system|>\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{% for tool in tools %}\n{%- if 'function' in tool -%}\n {%- set tool = tool['function'] -%}\n{%- endif -%}\n{% if tool.defer_loading is not defined or not tool.defer_loading %}\n{{ tool_to_json(tool) }}\n{% endif %}\n{% endfor %}\n</tools>\n\nFor each function call, output the function name and arguments within the following XML format:\n<tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}\n{%- macro emit_image() -%}<|begin_of_image|><|image|><|end_of_image|>{%- endmacro -%}\n{%- macro emit_video() -%}<|begin_of_video|><|video|><|end_of_video|>{%- endmacro -%}\n{%- macro emit_audio() -%}<|begin_of_audio|><|end_of_audio|>{%- endmacro -%}\n{%- macro visible_text(content) -%}\n {%- if content is string -%}\n {{- content -}}\n {%- elif content is iterable and content is not mapping -%}\n {%- for item in content -%}\n {%- if item is mapping and item.type == 'text' -%}\n {{- item.text -}}\n {%- elif item is string -%}\n {{- item -}}\n {%- elif item is mapping and item.type in ['image', 'image_url'] -%}\n {{- emit_image() -}}\n {%- elif item is mapping and item.type in ['video', 'video_url'] -%}\n {{- emit_video() -}}\n {%- elif item is mapping and item.type in ['audio', 'audio_url', 'input_audio'] -%}\n {{- emit_audio() -}}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{- content }}\n {%- endif -%}\n{%- endmacro -%}\n{%- macro tool_response(text) -%}\n{{- '<tool_response>' + text + '</tool_response>' -}}\n{%- endmacro -%}\n{%- macro render_tool_response(m) -%}\n{%- if m.content is string -%}\n {{- tool_response(m.content) -}}\n{%- elif m.content and m.content is not mapping and m.content.0.type == \"tool_reference\" -%}\n {{- tool_references_to_response(m.content) -}}\n{%- elif is_list_of_outputs(m) -%}\n {%- for tr in m.content -%}\n {%- if tr.output is iterable and tr.output is not string and tr.output is not mapping and tr.output and tr.output.0.type == \"tool_reference\" -%}\n {{- tool_references_to_response(tr.output) -}}\n {%- else -%}\n {{- tool_response(visible_text(tr.output)) -}}\n {%- endif -%}\n {%- endfor -%}\n{%- else -%}\n {{- tool_response(visible_text(m.content)) -}}\n{%- endif -%}\n{%- endmacro -%}\n{%- macro id_of(obj) -%}\n {%- if obj.tool_call_id -%}\n {{- obj.tool_call_id -}}\n {%- elif obj.id -%}\n {{- obj.id -}}\n {%- endif -%}\n{%- endmacro -%}\n{%- macro is_list_of_outputs(m) -%}\n {%- if m.content and m.content.0.output is defined -%}1{%- endif -%}\n{%- endmacro -%}\n{%- macro has_dup_tool_result_id(lo, hi, target) -%}\n {%- set ns_cnt = namespace(n=0) -%}\n {%- for k in range(lo, hi + 1) -%}\n {%- set m = messages[k] -%}\n {%- if is_list_of_outputs(m) -%}\n {%- for entry in m.content -%}\n {%- if id_of(entry) == target -%}\n {%- set ns_cnt.n = ns_cnt.n + 1 -%}\n {%- endif -%}\n {%- endfor -%}\n {%- elif id_of(m) == target -%}\n {%- set ns_cnt.n = ns_cnt.n + 1 -%}\n {%- endif -%}\n {%- if ns_cnt.n > 1 -%}{%- break -%}{%- endif -%}\n {%- endfor -%}\n {%- if ns_cnt.n > 1 -%}1{%- endif -%}\n{%- endmacro -%}\n{%- macro tc_id_exists(tcs, target) -%}\n {%- set ns_f = namespace(found=false) -%}\n {%- for tc in tcs -%}\n {%- if id_of(tc) == target -%}\n {%- set ns_f.found = true -%}\n {%- break -%}\n {%- endif -%}\n {%- endfor -%}\n {%- if ns_f.found -%}1{%- endif -%}\n{%- endmacro -%}\n{%- set ns = namespace(last_user_index=-1) -%}\n{%- for m in messages %}\n {%- if m.role == 'user' %}\n {%- set ns.last_user_index = loop.index0 -%}\n {%- endif %}\n{%- endfor %}\n{%- for m in messages -%}\n{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}\n{%- elif m.role == 'assistant' -%}\n<|assistant|>\n{%- set content = visible_text(m.content) %}\n{%- if m.reasoning_content is string %}\n {%- set reasoning_content = m.reasoning_content %}\n{%- elif '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}\n {%- set content = content.split('</think>')[-1] %}\n{%- endif %}\n{%- if (not clear_thinking or loop.index0 > ns.last_user_index) and reasoning_content is defined -%}\n{{ '<think>' + reasoning_content + '</think>'}}\n{%- else -%}\n{{ '<think></think>' }}\n{%- endif -%}\n{%- if content.strip() -%}\n{{ content.strip() }}\n{%- endif -%}\n{% if m.tool_calls %}\n{% for tc in m.tool_calls %}\n{%- if tc.function %}\n {%- set tc = tc.function %}\n{%- endif %}\n{{- '<tool_call>' + tc.name -}}\n{% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}\n{% endif %}\n{%- elif m.role == 'tool' -%}\n{%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|observation|>' -}}\n {%- set block_start = loop.index0 -%}\n {%- set ns_blk = namespace(end=block_start) -%}\n {%- for j in range(block_start, messages|length) -%}\n {%- if messages[j].role == 'tool' -%}\n {%- set ns_blk.end = j -%}\n {%- else -%}\n {%- break -%}\n {%- endif -%}\n {%- endfor -%}\n {%- set ns_a = namespace(tool_calls=none) -%}\n {%- if block_start > 0 and messages[block_start - 1].role == 'assistant' and messages[block_start - 1].tool_calls -%}\n {%- set ns_a.tool_calls = messages[block_start - 1].tool_calls -%}\n {%- endif -%}\n {%- set ns_chk = namespace(can_sort=true) -%}\n {%- if not ns_a.tool_calls -%}\n {%- set ns_chk.can_sort = false -%}\n {%- else -%}\n {%- for k in range(block_start, ns_blk.end + 1) -%}\n {%- set m = messages[k] -%}\n {%- if is_list_of_outputs(m) -%}\n {%- for entry in m.content -%}\n {%- set eid = id_of(entry) -%}\n {%- if not eid -%}\n {%- set ns_chk.can_sort = false -%}\n {%- elif has_dup_tool_result_id(block_start, ns_blk.end, eid) -%}\n {%- set ns_chk.can_sort = false -%}\n {%- elif not tc_id_exists(ns_a.tool_calls, eid) -%}\n {%- set ns_chk.can_sort = false -%}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {%- set tk_id = id_of(m) -%}\n {%- if not tk_id -%}\n {%- set ns_chk.can_sort = false -%}\n {%- elif has_dup_tool_result_id(block_start, ns_blk.end, tk_id) -%}\n {%- set ns_chk.can_sort = false -%}\n {%- elif not tc_id_exists(ns_a.tool_calls, tk_id) -%}\n {%- set ns_chk.can_sort = false -%}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n {%- for i in range(ns_a.tool_calls | length) -%}\n {%- set tc_id = id_of(ns_a.tool_calls[i]) -%}\n {%- if not tc_id -%}\n {%- set ns_chk.can_sort = false -%}\n {%- endif -%}\n {%- for j in range(i + 1, ns_a.tool_calls | length) -%}\n {%- if id_of(ns_a.tool_calls[j]) == tc_id -%}\n {%- set ns_chk.can_sort = false -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endfor -%}\n {%- endif -%}\n {%- if ns_chk.can_sort -%}\n {%- for tc in ns_a.tool_calls -%}\n {%- set tc_id = id_of(tc) -%}\n {%- for k in range(block_start, ns_blk.end + 1) -%}\n {%- set m = messages[k] -%}\n {%- if is_list_of_outputs(m) -%}\n {%- for entry in m.content -%}\n {%- set eid = id_of(entry) -%}\n {%- if eid == tc_id -%}\n {%- if entry.output is iterable and entry.output is not string and entry.output is not mapping and entry.output and entry.output.0.type == \"tool_reference\" -%}\n {{- tool_references_to_response(entry.output) -}}\n {%- else -%}\n {{- tool_response(visible_text(entry.output)) -}}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n{%- else -%}\n {%- set tk_id = id_of(m) -%}\n {%- if tk_id == tc_id -%}\n {{- render_tool_response(m) -}}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endfor -%}\n {%- else -%}\n {%- for k in range(block_start, ns_blk.end + 1) -%}\n {{- render_tool_response(messages[k]) -}}\n {%- endfor -%}\n {%- endif -%}\n{% endif -%}\n{%- elif m.role == 'system' -%}\n<|system|>{{ visible_text(m.content) }}\n{%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n <|assistant|>{{- '<think>' -}}\n{%- endif -%}\n",
"model_type": "glm5_next",
"quantization_config": {
"modules_to_not_convert": [
"attn_mha",
"attn_mqa",
"dt_bias",
"hyper_connection",
"lm_head",
"mapping_proj",
"model.embed_tokens",
"model.layers.0.hc_attn_base",
"model.layers.0.hc_attn_fn",
"model.layers.0.hc_attn_scale",
"model.layers.0.hc_ffn_base",
"model.layers.0.hc_ffn_fn",
"model.layers.0.hc_ffn_scale",
"model.layers.0.input_layernorm",
"model.layers.0.post_attention_layernorm",
"model.layers.0.self_attn.A_log",
"model.layers.0.self_attn.b_proj",
"model.layers.0.self_attn.dt_bias",
"model.layers.0.self_attn.f_a_proj",
"model.layers.0.self_attn.f_b_proj",
"model.layers.0.self_attn.fused_qkvbfg_a_proj",
"model.layers.0.self_attn.g_a_proj",
"model.layers.0.self_attn.g_b_proj",
"model.layers.0.self_attn.k_conv1d",
"model.layers.0.self_attn.k_proj",
"model.layers.0.self_attn.o_norm",
"model.layers.0.self_attn.o_proj",
"model.layers.0.self_attn.q_conv1d",
"model.layers.0.self_attn.q_proj",
"model.layers.0.self_attn.qkv_proj",
"model.layers.0.self_attn.v_conv1d",
"model.layers.0.self_attn.v_proj",
"model.layers.1.hc_attn_base",
"model.layers.1.hc_attn_fn",
"model.layers.1.hc_attn_scale",
"model.layers.1.hc_ffn_base",
"model.layers.1.hc_ffn_fn",
"model.layers.1.hc_ffn_scale",
"model.layers.1.input_layernorm",
"model.layers.1.post_attention_layernorm",
"model.layers.1.self_attn.A_log",
"model.layers.1.self_attn.b_proj",
"model.layers.1.self_attn.dt_bias",
"model.layers.1.self_attn.f_a_proj",
"model.layers.1.self_attn.f_b_proj",
"model.layers.1.self_attn.fused_qkvbfg_a_proj",
"model.layers.1.self_attn.g_a_proj",
"model.layers.1.self_attn.g_b_proj",
"model.layers.1.self_attn.k_conv1d",
"model.layers.1.self_attn.k_proj",
"model.layers.1.self_attn.o_norm",
"model.layers.1.self_attn.o_proj",
"model.layers.1.self_attn.q_conv1d",
"model.layers.1.self_attn.q_proj",
"model.layers.1.self_attn.qkv_proj",
"model.layers.1.self_attn.v_conv1d",
"model.layers.1.self_attn.v_proj",
"model.layers.10.hc_attn_base",
"model.layers.10.hc_attn_fn",
"model.layers.10.hc_attn_scale",
"model.layers.10.hc_ffn_base",
"model.layers.10.hc_ffn_fn",
"model.layers.10.hc_ffn_scale",
"model.layers.10.input_layernorm",
"model.layers.10.mlp.gate",
"model.layers.10.mlp.gate.e_score_correction_bias",
"model.layers.10.post_attention_layernorm",
"model.layers.10.self_attn.A_log",
"model.layers.10.self_attn.b_proj",
"model.layers.10.self_attn.dt_bias",
"model.layers.10.self_attn.f_a_proj",
"model.layers.10.self_attn.f_b_proj",
"model.layers.10.self_attn.fused_qkvbfg_a_proj",
"model.layers.10.self_attn.g_a_proj",
"model.layers.10.self_attn.g_b_proj",
"model.layers.10.self_attn.k_conv1d",
"model.layers.10.self_attn.k_proj",
"model.layers.10.self_attn.o_norm",
"model.layers.10.self_attn.o_proj",
"model.layers.10.self_attn.q_conv1d",
"model.layers.10.self_attn.q_proj",
"model.layers.10.self_attn.qkv_proj",
"model.layers.10.self_attn.v_conv1d",
"model.layers.10.self_attn.v_proj",
"model.layers.11.hc_attn_base",
"model.layers.11.hc_attn_fn",
"model.layers.11.hc_attn_scale",
"model.layers.11.hc_ffn_base",
"model.layers.11.hc_ffn_fn",
"model.layers.11.hc_ffn_scale",
"model.layers.11.input_layernorm",
"model.layers.11.mlp.gate",
"model.layers.11.mlp.gate.e_score_correction_bias",
"model.layers.11.post_attention_layernorm",
"model.layers.11.self_attn.indexer.index_kpool_compress_ape",
"model.layers.11.self_attn.indexer.index_kpool_compress_gate",
"model.layers.11.self_attn.indexer.k_norm",
"model.layers.11.self_attn.indexer.k_norm.bias",
"model.layers.11.self_attn.indexer.weights_proj",
"model.layers.11.self_attn.indexer.wk",
"model.layers.11.self_attn.indexer.wq_b",
"model.layers.11.self_attn.kv_a_layernorm",
"model.layers.11.self_attn.kv_b_proj",
"model.layers.11.self_attn.q_a_layernorm",
"model.layers.12.hc_attn_base",
"model.layers.12.hc_attn_fn",
"model.layers.12.hc_attn_scale",
"model.layers.12.hc_ffn_base",
"model.layers.12.hc_ffn_fn",
"model.layers.12.hc_ffn_scale",
"model.layers.12.input_layernorm",
"model.layers.12.mlp.gate",
"model.layers.12.mlp.gate.e_score_correction_bias",
"model.layers.12.post_attention_layernorm",
"model.layers.12.self_attn.A_log",
"model.layers.12.self_attn.b_proj",
"model.layers.12.self_attn.dt_bias",
"model.layers.12.self_attn.f_a_proj",
"model.layers.12.self_attn.f_b_proj",
"model.layers.12.self_attn.fused_qkvbfg_a_proj",
"model.layers.12.self_attn.g_a_proj",
"model.layers.12.self_attn.g_b_proj",
"model.layers.12.self_attn.k_conv1d",
"model.layers.12.self_attn.k_proj",
"model.layers.12.self_attn.o_norm",
"model.layers.12.self_attn.o_proj",
"model.layers.12.self_attn.q_conv1d",
"model.layers.12.self_attn.q_proj",
"model.layers.12.self_attn.qkv_proj",
"model.layers.12.self_attn.v_conv1d",
"model.layers.12.self_attn.v_proj",
"model.layers.13.hc_attn_base",
"model.layers.13.hc_attn_fn",
"model.layers.13.hc_attn_scale",
"model.layers.13.hc_ffn_base",
"model.layers.13.hc_ffn_fn",
"model.layers.13.hc_ffn_scale",
"model.layers.13.input_layernorm",
"model.layers.13.mlp.gate",
"model.layers.13.mlp.gate.e_score_correction_bias",
"model.layers.13.post_attention_layernorm",
"model.layers.13.self_attn.A_log",
"model.layers.13.self_attn.b_proj",
"model.layers.13.self_attn.dt_bias",
"model.layers.13.self_attn.f_a_proj",
"model.layers.13.self_attn.f_b_proj",
"model.layers.13.self_attn.fused_qkvbfg_a_proj",
"model.layers.13.self_attn.g_a_proj",
"model.layers.13.self_attn.g_b_proj",
"model.layers.13.self_attn.k_conv1d",
"model.layers.13.self_attn.k_proj",
"model.layers.13.self_attn.o_norm",
"model.layers.13.self_attn.o_proj",
"model.layers.13.self_attn.q_conv1d",
"model.layers.13.self_attn.q_proj",
"model.layers.13.self_attn.qkv_proj",
"model.layers.13.self_attn.v_conv1d",
"model.layers.13.self_attn.v_proj",
"model.layers.14.hc_attn_base",
"model.layers.14.hc_attn_fn",
"model.layers.14.hc_attn_scale",
"model.layers.14.hc_ffn_base",
"model.layers.14.hc_ffn_fn",
"model.layers.14.hc_ffn_scale",
"model.layers.14.input_layernorm",
"model.layers.14.mlp.gate",
"model.layers.14.mlp.gate.e_score_correction_bias",
"model.layers.14.post_attention_layernorm",
"model.layers.14.self_attn.A_log",
"model.layers.14.self_attn.b_proj",
"model.layers.14.self_attn.dt_bias",
"model.layers.14.self_attn.f_a_proj",
"model.layers.14.self_attn.f_b_proj",
"model.layers.14.self_attn.fused_qkvbfg_a_proj",
"model.layers.14.self_attn.g_a_proj",
"model.layers.14.self_attn.g_b_proj",
"model.layers.14.self_attn.k_conv1d",
"model.layers.14.self_attn.k_proj",
"model.layers.14.self_attn.o_norm",
"model.layers.14.self_attn.o_proj",
"model.layers.14.self_attn.q_conv1d",
"model.layers.14.self_attn.q_proj",
"model.layers.14.self_attn.qkv_proj",
"model.layers.14.self_attn.v_conv1d",
"model.layers.14.self_attn.v_proj",
"model.layers.15.hc_attn_base",
"model.layers.15.hc_attn_fn",
"model.layers.15.hc_attn_scale",
"model.layers.15.hc_ffn_base",
"model.layers.15.hc_ffn_fn",
"model.layers.15.hc_ffn_scale",
"model.layers.15.input_layernorm",
"model.layers.15.mlp.gate",
"model.layers.15.mlp.gate.e_score_correction_bias",
"model.layers.15.post_attention_layernorm",
"model.layers.15.self_attn.indexer.index_kpool_compress_ape",
"model.layers.15.self_attn.indexer.index_kpool_compress_gate",
"model.layers.15.self_attn.indexer.k_norm",
"model.layers.15.self_attn.indexer.k_norm.bias",
"model.layers.15.self_attn.indexer.weights_proj",
"model.layers.15.self_attn.indexer.wk",
"model.layers.15.self_attn.indexer.wq_b",
"model.layers.15.self_attn.kv_a_layernorm",
"model.layers.15.self_attn.kv_b_proj",
"model.layers.15.self_attn.q_a_layernorm",
"model.layers.16.hc_attn_base",
"model.layers.16.hc_attn_fn",
"model.layers.16.hc_attn_scale",
"model.layers.16.hc_ffn_base",
"model.layers.16.hc_ffn_fn",
"model.layers.16.hc_ffn_scale",
"model.layers.16.input_layernorm",
"model.layers.16.mlp.gate",
"model.layers.16.mlp.gate.e_score_correction_bias",
"model.layers.16.post_attention_layernorm",
"model.layers.16.self_attn.A_log",
"model.layers.16.self_attn.b_proj",
"model.layers.16.self_attn.dt_bias",
"model.layers.16.self_attn.f_a_proj",
"model.layers.16.self_attn.f_b_proj",
"model.layers.16.self_attn.fused_qkvbfg_a_proj",
"model.layers.16.self_attn.g_a_proj",
"model.layers.16.self_attn.g_b_proj",
"model.layers.16.self_attn.k_conv1d",
"model.layers.16.self_attn.k_proj",
"model.layers.16.self_attn.o_norm",
"model.layers.16.self_attn.o_proj",
"model.layers.16.self_attn.q_conv1d",
"model.layers.16.self_attn.q_proj",
"model.layers.16.self_attn.qkv_proj",
"model.layers.16.self_attn.v_conv1d",
"model.layers.16.self_attn.v_proj",
"model.layers.17.hc_attn_base",
"model.layers.17.hc_attn_fn",
"model.layers.17.hc_attn_scale",
"model.layers.17.hc_ffn_base",
"model.layers.17.hc_ffn_fn",
"model.layers.17.hc_ffn_scale",
"model.layers.17.input_layernorm",
"model.layers.17.mlp.gate",
"model.layers.17.mlp.gate.e_score_correction_bias",
"model.layers.17.post_attention_layernorm",
"model.layers.17.self_attn.A_log",
"model.layers.17.self_attn.b_proj",
"model.layers.17.self_attn.dt_bias",
"model.layers.17.self_attn.f_a_proj",
"model.layers.17.self_attn.f_b_proj",
"model.layers.17.self_attn.fused_qkvbfg_a_proj",
"model.layers.17.self_attn.g_a_proj",
"model.layers.17.self_attn.g_b_proj",
"model.layers.17.self_attn.k_conv1d",
"model.layers.17.self_attn.k_proj",
"model.layers.17.self_attn.o_norm",
"model.layers.17.self_attn.o_proj",
"model.layers.17.self_attn.q_conv1d",
"model.layers.17.self_attn.q_proj",
"model.layers.17.self_attn.qkv_proj",
"model.layers.17.self_attn.v_conv1d",
"model.layers.17.self_attn.v_proj",
"model.layers.18.hc_attn_base",
"model.layers.18.hc_attn_fn",
"model.layers.18.hc_attn_scale",
"model.layers.18.hc_ffn_base",
"model.layers.18.hc_ffn_fn",
"model.layers.18.hc_ffn_scale",
"model.layers.18.input_layernorm",
"model.layers.18.mlp.gate",
"model.layers.18.mlp.gate.e_score_correction_bias",
"model.layers.18.post_attention_layernorm",
"model.layers.18.self_attn.A_log",
"model.layers.18.self_attn.b_proj",
"model.layers.18.self_attn.dt_bias",
"model.layers.18.self_attn.f_a_proj",
"model.layers.18.self_attn.f_b_proj",
"model.layers.18.self_attn.fused_qkvbfg_a_proj",
"model.layers.18.self_attn.g_a_proj",
"model.layers.18.self_attn.g_b_proj",
"model.layers.18.self_attn.k_conv1d",
"model.layers.18.self_attn.k_proj",
"model.layers.18.self_attn.o_norm",
"model.layers.18.self_attn.o_proj",
"model.layers.18.self_attn.q_conv1d",
"model.layers.18.self_attn.q_proj",
"model.layers.18.self_attn.qkv_proj",
"model.layers.18.self_attn.v_conv1d",
"model.layers.18.self_attn.v_proj",
"model.layers.19.hc_attn_base",
"model.layers.19.hc_attn_fn",
"model.layers.19.hc_attn_scale",
"model.layers.19.hc_ffn_base",
"model.layers.19.hc_ffn_fn",
"model.layers.19.hc_ffn_scale",
"model.layers.19.input_layernorm",
"model.layers.19.mlp.gate",
"model.layers.19.mlp.gate.e_score_correction_bias",
"model.layers.19.post_attention_layernorm",
"model.layers.19.self_attn.indexer.index_kpool_compress_ape",
"model.layers.19.self_attn.indexer.index_kpool_compress_gate",
"model.layers.19.self_attn.indexer.k_norm",
"model.layers.19.self_attn.indexer.k_norm.bias",
"model.layers.19.self_attn.indexer.weights_proj",
"model.layers.19.self_attn.indexer.wk",
"model.layers.19.self_attn.indexer.wq_b",
"model.layers.19.self_attn.kv_a_layernorm",
"model.layers.19.self_attn.kv_b_proj",
"model.layers.19.self_attn.q_a_layernorm",
"model.layers.2.hc_attn_base",
"model.layers.2.hc_attn_fn",
"model.layers.2.hc_attn_scale",
"model.layers.2.hc_ffn_base",
"model.layers.2.hc_ffn_fn",
"model.layers.2.hc_ffn_scale",
"model.layers.2.input_layernorm",
"model.layers.2.post_attention_layernorm",
"model.layers.2.self_attn.A_log",
"model.layers.2.self_attn.b_proj",
"model.layers.2.self_attn.dt_bias",
"model.layers.2.self_attn.f_a_proj",
"model.layers.2.self_attn.f_b_proj",
"model.layers.2.self_attn.fused_qkvbfg_a_proj",
"model.layers.2.self_attn.g_a_proj",
"model.layers.2.self_attn.g_b_proj",
"model.layers.2.self_attn.k_conv1d",
"model.layers.2.self_attn.k_proj",
"model.layers.2.self_attn.o_norm",
"model.layers.2.self_attn.o_proj",
"model.layers.2.self_attn.q_conv1d",
"model.layers.2.self_attn.q_proj",
"model.layers.2.self_attn.qkv_proj",
"model.layers.2.self_attn.v_conv1d",
"model.layers.2.self_attn.v_proj",
"model.layers.20.hc_attn_base",
"model.layers.20.hc_attn_fn",
"model.layers.20.hc_attn_scale",
"model.layers.20.hc_ffn_base",
"model.layers.20.hc_ffn_fn",
"model.layers.20.hc_ffn_scale",
"model.layers.20.input_layernorm",
"model.layers.20.mlp.gate",
"model.layers.20.mlp.gate.e_score_correction_bias",
"model.layers.20.post_attention_layernorm",
"model.layers.20.self_attn.A_log",
"model.layers.20.self_attn.b_proj",
"model.layers.20.self_attn.dt_bias",
"model.layers.20.self_attn.f_a_proj",
"model.layers.20.self_attn.f_b_proj",
"model.layers.20.self_attn.fused_qkvbfg_a_proj",
"model.layers.20.self_attn.g_a_proj",
"model.layers.20.self_attn.g_b_proj",
"model.layers.20.self_attn.k_conv1d",
"model.layers.20.self_attn.k_proj",
"model.layers.20.self_attn.o_norm",
"model.layers.20.self_attn.o_proj",
"model.layers.20.self_attn.q_conv1d",
"model.layers.20.self_attn.q_proj",
"model.layers.20.self_attn.qkv_proj",
"model.layers.20.self_attn.v_conv1d",
"model.layers.20.self_attn.v_proj",
"model.layers.21.hc_attn_base",
"model.layers.21.hc_attn_fn",
"model.layers.21.hc_attn_scale",
"model.layers.21.hc_ffn_base",
"model.layers.21.hc_ffn_fn",
"model.layers.21.hc_ffn_scale",
"model.layers.21.input_layernorm",
"model.layers.21.mlp.gate",
"model.layers.21.mlp.gate.e_score_correction_bias",
"model.layers.21.post_attention_layernorm",
"model.layers.21.self_attn.A_log",
"model.layers.21.self_attn.b_proj",
"model.layers.21.self_attn.dt_bias",
"model.layers.21.self_attn.f_a_proj",
"model.layers.21.self_attn.f_b_proj",
"model.layers.21.self_attn.fused_qkvbfg_a_proj",
"model.layers.21.self_attn.g_a_proj",
"model.layers.21.self_attn.g_b_proj",
"model.layers.21.self_attn.k_conv1d",
"model.layers.21.self_attn.k_proj",
"model.layers.21.self_attn.o_norm",
"model.layers.21.self_attn.o_proj",
"model.layers.21.self_attn.q_conv1d",
"model.layers.21.self_attn.q_proj",
"model.layers.21.self_attn.qkv_proj",
"model.layers.21.self_attn.v_conv1d",
"model.layers.21.self_attn.v_proj",
"model.layers.22.hc_attn_base",
"model.layers.22.hc_attn_fn",
"model.layers.22.hc_attn_scale",
"model.layers.22.hc_ffn_base",
"model.layers.22.hc_ffn_fn",
"model.layers.22.hc_ffn_scale",
"model.layers.22.input_layernorm",
"model.layers.22.mlp.gate",
"model.layers.22.mlp.gate.e_score_correction_bias",
"model.layers.22.post_attention_layernorm",
"model.layers.22.self_attn.A_log",
"model.layers.22.self_attn.b_proj",
"model.layers.22.self_attn.dt_bias",
"model.layers.22.self_attn.f_a_proj",
"model.layers.22.self_attn.f_b_proj",
"model.layers.22.self_attn.fused_qkvbfg_a_proj",
"model.layers.22.self_attn.g_a_proj",
"model.layers.22.self_attn.g_b_proj",
"model.layers.22.self_attn.k_conv1d",
"model.layers.22.self_attn.k_proj",
"model.layers.22.self_attn.o_norm",
"model.layers.22.self_attn.o_proj",
"model.layers.22.self_attn.q_conv1d",
"model.layers.22.self_attn.q_proj",
"model.layers.22.self_attn.qkv_proj",
"model.layers.22.self_attn.v_conv1d",
"model.layers.22.self_attn.v_proj",
"model.layers.23.hc_attn_base",
"model.layers.23.hc_attn_fn",
"model.layers.23.hc_attn_scale",
"model.layers.23.hc_ffn_base",
"model.layers.23.hc_ffn_fn",
"model.layers.23.hc_ffn_scale",
"model.layers.23.input_layernorm",
"model.layers.23.mlp.gate",
"model.layers.23.mlp.gate.e_score_correction_bias",
"model.layers.23.post_attention_layernorm",
"model.layers.23.self_attn.indexer.index_kpool_compress_ape",
"model.layers.23.self_attn.indexer.index_kpool_compress_gate",
"model.layers.23.self_attn.indexer.k_norm",
"model.layers.23.self_attn.indexer.k_norm.bias",
"model.layers.23.self_attn.indexer.weights_proj",
"model.layers.23.self_attn.indexer.wk",
"model.layers.23.self_attn.indexer.wq_b",
"model.layers.23.self_attn.kv_a_layernorm",
"model.layers.23.self_attn.kv_b_proj",
"model.layers.23.self_attn.q_a_layernorm",
"model.layers.24.hc_attn_base",
"model.layers.24.hc_attn_fn",
"model.layers.24.hc_attn_scale",
"model.layers.24.hc_ffn_base",
"model.layers.24.hc_ffn_fn",
"model.layers.24.hc_ffn_scale",
"model.layers.24.input_layernorm",
"model.layers.24.mlp.gate",
"model.layers.24.mlp.gate.e_score_correction_bias",
"model.layers.24.post_attention_layernorm",
"model.layers.24.self_attn.A_log",
"model.layers.24.self_attn.b_proj",
"model.layers.24.self_attn.dt_bias",
"model.layers.24.self_attn.f_a_proj",
"model.layers.24.self_attn.f_b_proj",
"model.layers.24.self_attn.fused_qkvbfg_a_proj",
"model.layers.24.self_attn.g_a_proj",
"model.layers.24.self_attn.g_b_proj",
"model.layers.24.self_attn.k_conv1d",
"model.layers.24.self_attn.k_proj",
"model.layers.24.self_attn.o_norm",
"model.layers.24.self_attn.o_proj",
"model.layers.24.self_attn.q_conv1d",
"model.layers.24.self_attn.q_proj",
"model.layers.24.self_attn.qkv_proj",
"model.layers.24.self_attn.v_conv1d",
"model.layers.24.self_attn.v_proj",
"model.layers.25.hc_attn_base",
"model.layers.25.hc_attn_fn",
"model.layers.25.hc_attn_scale",
"model.layers.25.hc_ffn_base",
"model.layers.25.hc_ffn_fn",
"model.layers.25.hc_ffn_scale",
"model.layers.25.input_layernorm",
"model.layers.25.mlp.gate",
"model.layers.25.mlp.gate.e_score_correction_bias",
"model.layers.25.post_attention_layernorm",
"model.layers.25.self_attn.A_log",
"model.layers.25.self_attn.b_proj",
"model.layers.25.self_attn.dt_bias",
"model.layers.25.self_attn.f_a_proj",
"model.layers.25.self_attn.f_b_proj",
"model.layers.25.self_attn.fused_qkvbfg_a_proj",
"model.layers.25.self_attn.g_a_proj",
"model.layers.25.self_attn.g_b_proj",
"model.layers.25.self_attn.k_conv1d",
"model.layers.25.self_attn.k_proj",
"model.layers.25.self_attn.o_norm",
"model.layers.25.self_attn.o_proj",
"model.layers.25.self_attn.q_conv1d",
"model.layers.25.self_attn.q_proj",
"model.layers.25.self_attn.qkv_proj",
"model.layers.25.self_attn.v_conv1d",
"model.layers.25.self_attn.v_proj",
"model.layers.26.hc_attn_base",
"model.layers.26.hc_attn_fn",
"model.layers.26.hc_attn_scale",
"model.layers.26.hc_ffn_base",
"model.layers.26.hc_ffn_fn",
"model.layers.26.hc_ffn_scale",
"model.layers.26.input_layernorm",
"model.layers.26.mlp.gate",
"model.layers.26.mlp.gate.e_score_correction_bias",
"model.layers.26.post_attention_layernorm",
"model.layers.26.self_attn.A_log",
"model.layers.26.self_attn.b_proj",
"model.layers.26.self_attn.dt_bias",
"model.layers.26.self_attn.f_a_proj",
"model.layers.26.self_attn.f_b_proj",
"model.layers.26.self_attn.fused_qkvbfg_a_proj",
"model.layers.26.self_attn.g_a_proj",
"model.layers.26.self_attn.g_b_proj",
"model.layers.26.self_attn.k_conv1d",
"model.layers.26.self_attn.k_proj",
"model.layers.26.self_attn.o_norm",
"model.layers.26.self_attn.o_proj",
"model.layers.26.self_attn.q_conv1d",
"model.layers.26.self_attn.q_proj",
"model.layers.26.self_attn.qkv_proj",
"model.layers.26.self_attn.v_conv1d",
"model.layers.26.self_attn.v_proj",
"model.layers.27.hc_attn_base",
"model.layers.27.hc_attn_fn",
"model.layers.27.hc_attn_scale",
"model.layers.27.hc_ffn_base",
"model.layers.27.hc_ffn_fn",
"model.layers.27.hc_ffn_scale",
"model.layers.27.input_layernorm",
"model.layers.27.mlp.gate",
"model.layers.27.mlp.gate.e_score_correction_bias",
"model.layers.27.post_attention_layernorm",
"model.layers.27.self_attn.indexer.index_kpool_compress_ape",
"model.layers.27.self_attn.indexer.index_kpool_compress_gate",
"model.layers.27.self_attn.indexer.k_norm",
"model.layers.27.self_attn.indexer.k_norm.bias",
"model.layers.27.self_attn.indexer.weights_proj",
"model.layers.27.self_attn.indexer.wk",
"model.layers.27.self_attn.indexer.wq_b",
"model.layers.27.self_attn.kv_a_layernorm",
"model.layers.27.self_attn.kv_b_proj",
"model.layers.27.self_attn.q_a_layernorm",
"model.layers.28.hc_attn_base",
"model.layers.28.hc_attn_fn",
"model.layers.28.hc_attn_scale",
"model.layers.28.hc_ffn_base",
"model.layers.28.hc_ffn_fn",
"model.layers.28.hc_ffn_scale",
"model.layers.28.input_layernorm",
"model.layers.28.mlp.gate",
"model.layers.28.mlp.gate.e_score_correction_bias",
"model.layers.28.post_attention_layernorm",
"model.layers.28.self_attn.A_log",
"model.layers.28.self_attn.b_proj",
"model.layers.28.self_attn.dt_bias",
"model.layers.28.self_attn.f_a_proj",
"model.layers.28.self_attn.f_b_proj",
"model.layers.28.self_attn.fused_qkvbfg_a_proj",
"model.layers.28.self_attn.g_a_proj",
"model.layers.28.self_attn.g_b_proj",
"model.layers.28.self_attn.k_conv1d",
"model.layers.28.self_attn.k_proj",
"model.layers.28.self_attn.o_norm",
"model.layers.28.self_attn.o_proj",
"model.layers.28.self_attn.q_conv1d",
"model.layers.28.self_attn.q_proj",
"model.layers.28.self_attn.qkv_proj",
"model.layers.28.self_attn.v_conv1d",
"model.layers.28.self_attn.v_proj",
"model.layers.29.hc_attn_base",
"model.layers.29.hc_attn_fn",
"model.layers.29.hc_attn_scale",
"model.layers.29.hc_ffn_base",
"model.layers.29.hc_ffn_fn",
"model.layers.29.hc_ffn_scale",
"model.layers.29.input_layernorm",
"model.layers.29.mlp.gate",
"model.layers.29.mlp.gate.e_score_correction_bias",
"model.layers.29.post_attention_layernorm",
"model.layers.29.self_attn.A_log",
"model.layers.29.self_attn.b_proj",
"model.layers.29.self_attn.dt_bias",
"model.layers.29.self_attn.f_a_proj",
"model.layers.29.self_attn.f_b_proj",
"model.layers.29.self_attn.fused_qkvbfg_a_proj",
"model.layers.29.self_attn.g_a_proj",
"model.layers.29.self_attn.g_b_proj",
"model.layers.29.self_attn.k_conv1d",
"model.layers.29.self_attn.k_proj",
"model.layers.29.self_attn.o_norm",
"model.layers.29.self_attn.o_proj",
"model.layers.29.self_attn.q_conv1d",
"model.layers.29.self_attn.q_proj",
"model.layers.29.self_attn.qkv_proj",
"model.layers.29.self_attn.v_conv1d",
"model.layers.29.self_attn.v_proj",
"model.layers.3.hc_attn_base",
"model.layers.3.hc_attn_fn",
"model.layers.3.hc_attn_scale",
"model.layers.3.hc_ffn_base",
"model.layers.3.hc_ffn_fn",
"model.layers.3.hc_ffn_scale",
"model.layers.3.input_layernorm",
"model.layers.3.mlp.gate",
"model.layers.3.mlp.gate.e_score_correction_bias",
"model.layers.3.post_attention_layernorm",
"model.layers.3.self_attn.indexer.index_kpool_compress_ape",
"model.layers.3.self_attn.indexer.index_kpool_compress_gate",
"model.layers.3.self_attn.indexer.k_norm",
"model.layers.3.self_attn.indexer.k_norm.bias",
"model.layers.3.self_attn.indexer.weights_proj",
"model.layers.3.self_attn.indexer.wk",
"model.layers.3.self_attn.indexer.wq_b",
"model.layers.3.self_attn.kv_a_layernorm",
"model.layers.3.self_attn.kv_b_proj",
"model.layers.3.self_attn.q_a_layernorm",
"model.layers.30.hc_attn_base",
"model.layers.30.hc_attn_fn",
"model.layers.30.hc_attn_scale",
"model.layers.30.hc_ffn_base",
"model.layers.30.hc_ffn_fn",
"model.layers.30.hc_ffn_scale",
"model.layers.30.input_layernorm",
"model.layers.30.mlp.gate",
"model.layers.30.mlp.gate.e_score_correction_bias",
"model.layers.30.post_attention_layernorm",
"model.layers.30.self_attn.A_log",
"model.layers.30.self_attn.b_proj",
"model.layers.30.self_attn.dt_bias",
"model.layers.30.self_attn.f_a_proj",
"model.layers.30.self_attn.f_b_proj",
"model.layers.30.self_attn.fused_qkvbfg_a_proj",
"model.layers.30.self_attn.g_a_proj",
"model.layers.30.self_attn.g_b_proj",
"model.layers.30.self_attn.k_conv1d",
"model.layers.30.self_attn.k_proj",
"model.layers.30.self_attn.o_norm",
"model.layers.30.self_attn.o_proj",
"model.layers.30.self_attn.q_conv1d",
"model.layers.30.self_attn.q_proj",
"model.layers.30.self_attn.qkv_proj",
"model.layers.30.self_attn.v_conv1d",
"model.layers.30.self_attn.v_proj",
"model.layers.31.hc_attn_base",
"model.layers.31.hc_attn_fn",
"model.layers.31.hc_attn_scale",
"model.layers.31.hc_ffn_base",
"model.layers.31.hc_ffn_fn",
"model.layers.31.hc_ffn_scale",
"model.layers.31.input_layernorm",
"model.layers.31.mlp.gate",
"model.layers.31.mlp.gate.e_score_correction_bias",
"model.layers.31.post_attention_layernorm",
"model.layers.31.self_attn.indexer.index_kpool_compress_ape",
"model.layers.31.self_attn.indexer.index_kpool_compress_gate",
"model.layers.31.self_attn.indexer.k_norm",
"model.layers.31.self_attn.indexer.k_norm.bias",
"model.layers.31.self_attn.indexer.weights_proj",
"model.layers.31.self_attn.indexer.wk",
"model.layers.31.self_attn.indexer.wq_b",
"model.layers.31.self_attn.kv_a_layernorm",
"model.layers.31.self_attn.kv_b_proj",
"model.layers.31.self_attn.q_a_layernorm",
"model.layers.32.hc_attn_base",
"model.layers.32.hc_attn_fn",
"model.layers.32.hc_attn_scale",
"model.layers.32.hc_ffn_base",
"model.layers.32.hc_ffn_fn",
"model.layers.32.hc_ffn_scale",
"model.layers.32.input_layernorm",
"model.layers.32.mlp.gate",
"model.layers.32.mlp.gate.e_score_correction_bias",
"model.layers.32.post_attention_layernorm",
"model.layers.32.self_attn.A_log",
"model.layers.32.self_attn.b_proj",
"model.layers.32.self_attn.dt_bias",
"model.layers.32.self_attn.f_a_proj",
"model.layers.32.self_attn.f_b_proj",
"model.layers.32.self_attn.fused_qkvbfg_a_proj",
"model.layers.32.self_attn.g_a_proj",
"model.layers.32.self_attn.g_b_proj",
"model.layers.32.self_attn.k_conv1d",
"model.layers.32.self_attn.k_proj",
"model.layers.32.self_attn.o_norm",
"model.layers.32.self_attn.o_proj",
"model.layers.32.self_attn.q_conv1d",
"model.layers.32.self_attn.q_proj",
"model.layers.32.self_attn.qkv_proj",
"model.layers.32.self_attn.v_conv1d",
"model.layers.32.self_attn.v_proj",
"model.layers.33.hc_attn_base",
"model.layers.33.hc_attn_fn",
"model.layers.33.hc_attn_scale",
"model.layers.33.hc_ffn_base",
"model.layers.33.hc_ffn_fn",
"model.layers.33.hc_ffn_scale",
"model.layers.33.input_layernorm",
"model.layers.33.mlp.gate",
"model.layers.33.mlp.gate.e_score_correction_bias",
"model.layers.33.post_attention_layernorm",
"model.layers.33.self_attn.A_log",
"model.layers.33.self_attn.b_proj",
"model.layers.33.self_attn.dt_bias",
"model.layers.33.self_attn.f_a_proj",
"model.layers.33.self_attn.f_b_proj",
"model.layers.33.self_attn.fused_qkvbfg_a_proj",
"model.layers.33.self_attn.g_a_proj",
"model.layers.33.self_attn.g_b_proj",
"model.layers.33.self_attn.k_conv1d",
"model.layers.33.self_attn.k_proj",
"model.layers.33.self_attn.o_norm",
"model.layers.33.self_attn.o_proj",
"model.layers.33.self_attn.q_conv1d",
"model.layers.33.self_attn.q_proj",
"model.layers.33.self_attn.qkv_proj",
"model.layers.33.self_attn.v_conv1d",
"model.layers.33.self_attn.v_proj",
"model.layers.34.hc_attn_base",
"model.layers.34.hc_attn_fn",
"model.layers.34.hc_attn_scale",
"model.layers.34.hc_ffn_base",
"model.layers.34.hc_ffn_fn",
"model.layers.34.hc_ffn_scale",
"model.layers.34.input_layernorm",
"model.layers.34.mlp.gate",
"model.layers.34.mlp.gate.e_score_correction_bias",
"model.layers.34.post_attention_layernorm",
"model.layers.34.self_attn.A_log",
"model.layers.34.self_attn.b_proj",
"model.layers.34.self_attn.dt_bias",
"model.layers.34.self_attn.f_a_proj",
"model.layers.34.self_attn.f_b_proj",
"model.layers.34.self_attn.fused_qkvbfg_a_proj",
"model.layers.34.self_attn.g_a_proj",
"model.layers.34.self_attn.g_b_proj",
"model.layers.34.self_attn.k_conv1d",
"model.layers.34.self_attn.k_proj",
"model.layers.34.self_attn.o_norm",
"model.layers.34.self_attn.o_proj",
"model.layers.34.self_attn.q_conv1d",
"model.layers.34.self_attn.q_proj",
"model.layers.34.self_attn.qkv_proj",
"model.layers.34.self_attn.v_conv1d",
"model.layers.34.self_attn.v_proj",
"model.layers.35.hc_attn_base",
"model.layers.35.hc_attn_fn",
"model.layers.35.hc_attn_scale",
"model.layers.35.hc_ffn_base",
"model.layers.35.hc_ffn_fn",
"model.layers.35.hc_ffn_scale",
"model.layers.35.input_layernorm",
"model.layers.35.mlp.gate",
"model.layers.35.mlp.gate.e_score_correction_bias",
"model.layers.35.post_attention_layernorm",
"model.layers.35.self_attn.indexer.index_kpool_compress_ape",
"model.layers.35.self_attn.indexer.index_kpool_compress_gate",
"model.layers.35.self_attn.indexer.k_norm",
"model.layers.35.self_attn.indexer.k_norm.bias",
"model.layers.35.self_attn.indexer.weights_proj",
"model.layers.35.self_attn.indexer.wk",
"model.layers.35.self_attn.indexer.wq_b",
"model.layers.35.self_attn.kv_a_layernorm",
"model.layers.35.self_attn.kv_b_proj",
"model.layers.35.self_attn.q_a_layernorm",
"model.layers.36.hc_attn_base",
"model.layers.36.hc_attn_fn",
"model.layers.36.hc_attn_scale",
"model.layers.36.hc_ffn_base",
"model.layers.36.hc_ffn_fn",
"model.layers.36.hc_ffn_scale",
"model.layers.36.input_layernorm",
"model.layers.36.mlp.gate",
"model.layers.36.mlp.gate.e_score_correction_bias",
"model.layers.36.post_attention_layernorm",
"model.layers.36.self_attn.A_log",
"model.layers.36.self_attn.b_proj",
"model.layers.36.self_attn.dt_bias",
"model.layers.36.self_attn.f_a_proj",
"model.layers.36.self_attn.f_b_proj",
"model.layers.36.self_attn.fused_qkvbfg_a_proj",
"model.layers.36.self_attn.g_a_proj",
"model.layers.36.self_attn.g_b_proj",
"model.layers.36.self_attn.k_conv1d",
"model.layers.36.self_attn.k_proj",
"model.layers.36.self_attn.o_norm",
"model.layers.36.self_attn.o_proj",
"model.layers.36.self_attn.q_conv1d",
"model.layers.36.self_attn.q_proj",
"model.layers.36.self_attn.qkv_proj",
"model.layers.36.self_attn.v_conv1d",
"model.layers.36.self_attn.v_proj",
"model.layers.37.hc_attn_base",
"model.layers.37.hc_attn_fn",
"model.layers.37.hc_attn_scale",
"model.layers.37.hc_ffn_base",
"model.layers.37.hc_ffn_fn",
"model.layers.37.hc_ffn_scale",
"model.layers.37.input_layernorm",
"model.layers.37.mlp.gate",
"model.layers.37.mlp.gate.e_score_correction_bias",
"model.layers.37.post_attention_layernorm",
"model.layers.37.self_attn.A_log",
"model.layers.37.self_attn.b_proj",
"model.layers.37.self_attn.dt_bias",
"model.layers.37.self_attn.f_a_proj",
"model.layers.37.self_attn.f_b_proj",
"model.layers.37.self_attn.fused_qkvbfg_a_proj",
"model.layers.37.self_attn.g_a_proj",
"model.layers.37.self_attn.g_b_proj",
"model.layers.37.self_attn.k_conv1d",
"model.layers.37.self_attn.k_proj",
"model.layers.37.self_attn.o_norm",
"model.layers.37.self_attn.o_proj",
"model.layers.37.self_attn.q_conv1d",
"model.layers.37.self_attn.q_proj",
"model.layers.37.self_attn.qkv_proj",
"model.layers.37.self_attn.v_conv1d",
"model.layers.37.self_attn.v_proj",
"model.layers.38.hc_attn_base",
"model.layers.38.hc_attn_fn",
"model.layers.38.hc_attn_scale",
"model.layers.38.hc_ffn_base",
"model.layers.38.hc_ffn_fn",
"model.layers.38.hc_ffn_scale",
"model.layers.38.input_layernorm",
"model.layers.38.mlp.gate",
"model.layers.38.mlp.gate.e_score_correction_bias",
"model.layers.38.post_attention_layernorm",
"model.layers.38.self_attn.A_log",
"model.layers.38.self_attn.b_proj",
"model.layers.38.self_attn.dt_bias",
"model.layers.38.self_attn.f_a_proj",
"model.layers.38.self_attn.f_b_proj",
"model.layers.38.self_attn.fused_qkvbfg_a_proj",
"model.layers.38.self_attn.g_a_proj",
"model.layers.38.self_attn.g_b_proj",
"model.layers.38.self_attn.k_conv1d",
"model.layers.38.self_attn.k_proj",
"model.layers.38.self_attn.o_norm",
"model.layers.38.self_attn.o_proj",
"model.layers.38.self_attn.q_conv1d",
"model.layers.38.self_attn.q_proj",
"model.layers.38.self_attn.qkv_proj",
"model.layers.38.self_attn.v_conv1d",
"model.layers.38.self_attn.v_proj",
"model.layers.39.hc_attn_base",
"model.layers.39.hc_attn_fn",
"model.layers.39.hc_attn_scale",
"model.layers.39.hc_ffn_base",
"model.layers.39.hc_ffn_fn",
"model.layers.39.hc_ffn_scale",
"model.layers.39.input_layernorm",
"model.layers.39.mlp.gate",
"model.layers.39.mlp.gate.e_score_correction_bias",
"model.layers.39.post_attention_layernorm",
"model.layers.39.self_attn.indexer.index_kpool_compress_ape",
"model.layers.39.self_attn.indexer.index_kpool_compress_gate",
"model.layers.39.self_attn.indexer.k_norm",
"model.layers.39.self_attn.indexer.k_norm.bias",
"model.layers.39.self_attn.indexer.weights_proj",
"model.layers.39.self_attn.indexer.wk",
"model.layers.39.self_attn.indexer.wq_b",
"model.layers.39.self_attn.kv_a_layernorm",
"model.layers.39.self_attn.kv_b_proj",
"model.layers.39.self_attn.q_a_layernorm",
"model.layers.4.hc_attn_base",
"model.layers.4.hc_attn_fn",
"model.layers.4.hc_attn_scale",
"model.layers.4.hc_ffn_base",
"model.layers.4.hc_ffn_fn",
"model.layers.4.hc_ffn_scale",
"model.layers.4.input_layernorm",
"model.layers.4.mlp.gate",
"model.layers.4.mlp.gate.e_score_correction_bias",
"model.layers.4.post_attention_layernorm",
"model.layers.4.self_attn.A_log",
"model.layers.4.self_attn.b_proj",
"model.layers.4.self_attn.dt_bias",
"model.layers.4.self_attn.f_a_proj",
"model.layers.4.self_attn.f_b_proj",
"model.layers.4.self_attn.fused_qkvbfg_a_proj",
"model.layers.4.self_attn.g_a_proj",
"model.layers.4.self_attn.g_b_proj",
"model.layers.4.self_attn.k_conv1d",
"model.layers.4.self_attn.k_proj",
"model.layers.4.self_attn.o_norm",
"model.layers.4.self_attn.o_proj",
"model.layers.4.self_attn.q_conv1d",
"model.layers.4.self_attn.q_proj",
"model.layers.4.self_attn.qkv_proj",
"model.layers.4.self_attn.v_conv1d",
"model.layers.4.self_attn.v_proj",
"model.layers.40.hc_attn_base",
"model.layers.40.hc_attn_fn",
"model.layers.40.hc_attn_scale",
"model.layers.40.hc_ffn_base",
"model.layers.40.hc_ffn_fn",
"model.layers.40.hc_ffn_scale",
"model.layers.40.input_layernorm",
"model.layers.40.mlp.gate",
"model.layers.40.mlp.gate.e_score_correction_bias",
"model.layers.40.post_attention_layernorm",
"model.layers.40.self_attn.A_log",
"model.layers.40.self_attn.b_proj",
"model.layers.40.self_attn.dt_bias",
"model.layers.40.self_attn.f_a_proj",
"model.layers.40.self_attn.f_b_proj",
"model.layers.40.self_attn.fused_qkvbfg_a_proj",
"model.layers.40.self_attn.g_a_proj",
"model.layers.40.self_attn.g_b_proj",
"model.layers.40.self_attn.k_conv1d",
"model.layers.40.self_attn.k_proj",
"model.layers.40.self_attn.o_norm",
"model.layers.40.self_attn.o_proj",
"model.layers.40.self_attn.q_conv1d",
"model.layers.40.self_attn.q_proj",
"model.layers.40.self_attn.qkv_proj",
"model.layers.40.self_attn.v_conv1d",
"model.layers.40.self_attn.v_proj",
"model.layers.41.hc_attn_base",
"model.layers.41.hc_attn_fn",
"model.layers.41.hc_attn_scale",
"model.layers.41.hc_ffn_base",
"model.layers.41.hc_ffn_fn",
"model.layers.41.hc_ffn_scale",
"model.layers.41.input_layernorm",
"model.layers.41.mlp.gate",
"model.layers.41.mlp.gate.e_score_correction_bias",
"model.layers.41.post_attention_layernorm",
"model.layers.41.self_attn.A_log",
"model.layers.41.self_attn.b_proj",
"model.layers.41.self_attn.dt_bias",
"model.layers.41.self_attn.f_a_proj",
"model.layers.41.self_attn.f_b_proj",
"model.layers.41.self_attn.fused_qkvbfg_a_proj",
"model.layers.41.self_attn.g_a_proj",
"model.layers.41.self_attn.g_b_proj",
"model.layers.41.self_attn.k_conv1d",
"model.layers.41.self_attn.k_proj",
"model.layers.41.self_attn.o_norm",
"model.layers.41.self_attn.o_proj",
"model.layers.41.self_attn.q_conv1d",
"model.layers.41.self_attn.q_proj",
"model.layers.41.self_attn.qkv_proj",
"model.layers.41.self_attn.v_conv1d",
"model.layers.41.self_attn.v_proj",
"model.layers.42.hc_attn_base",
"model.layers.42.hc_attn_fn",
"model.layers.42.hc_attn_scale",
"model.layers.42.hc_ffn_base",
"model.layers.42.hc_ffn_fn",
"model.layers.42.hc_ffn_scale",
"model.layers.42.input_layernorm",
"model.layers.42.mlp.gate",
"model.layers.42.mlp.gate.e_score_correction_bias",
"model.layers.42.post_attention_layernorm",
"model.layers.42.self_attn.A_log",
"model.layers.42.self_attn.b_proj",
"model.layers.42.self_attn.dt_bias",
"model.layers.42.self_attn.f_a_proj",
"model.layers.42.self_attn.f_b_proj",
"model.layers.42.self_attn.fused_qkvbfg_a_proj",
"model.layers.42.self_attn.g_a_proj",
"model.layers.42.self_attn.g_b_proj",
"model.layers.42.self_attn.k_conv1d",
"model.layers.42.self_attn.k_proj",
"model.layers.42.self_attn.o_norm",
"model.layers.42.self_attn.o_proj",
"model.layers.42.self_attn.q_conv1d",
"model.layers.42.self_attn.q_proj",
"model.layers.42.self_attn.qkv_proj",
"model.layers.42.self_attn.v_conv1d",
"model.layers.42.self_attn.v_proj",
"model.layers.43.hc_attn_base",
"model.layers.43.hc_attn_fn",
"model.layers.43.hc_attn_scale",
"model.layers.43.hc_ffn_base",
"model.layers.43.hc_ffn_fn",
"model.layers.43.hc_ffn_scale",
"model.layers.43.input_layernorm",
"model.layers.43.mlp.gate",
"model.layers.43.mlp.gate.e_score_correction_bias",
"model.layers.43.post_attention_layernorm",
"model.layers.43.self_attn.indexer.index_kpool_compress_ape",
"model.layers.43.self_attn.indexer.index_kpool_compress_gate",
"model.layers.43.self_attn.indexer.k_norm",
"model.layers.43.self_attn.indexer.k_norm.bias",
"model.layers.43.self_attn.indexer.weights_proj",
"model.layers.43.self_attn.indexer.wk",
"model.layers.43.self_attn.indexer.wq_b",
"model.layers.43.self_attn.kv_a_layernorm",
"model.layers.43.self_attn.kv_b_proj",
"model.layers.43.self_attn.q_a_layernorm",
"model.layers.44.hc_attn_base",
"model.layers.44.hc_attn_fn",
"model.layers.44.hc_attn_scale",
"model.layers.44.hc_ffn_base",
"model.layers.44.hc_ffn_fn",
"model.layers.44.hc_ffn_scale",
"model.layers.44.input_layernorm",
"model.layers.44.mlp.gate",
"model.layers.44.mlp.gate.e_score_correction_bias",
"model.layers.44.post_attention_layernorm",
"model.layers.44.self_attn.A_log",
"model.layers.44.self_attn.b_proj",
"model.layers.44.self_attn.dt_bias",
"model.layers.44.self_attn.f_a_proj",
"model.layers.44.self_attn.f_b_proj",
"model.layers.44.self_attn.fused_qkvbfg_a_proj",
"model.layers.44.self_attn.g_a_proj",
"model.layers.44.self_attn.g_b_proj",
"model.layers.44.self_attn.k_conv1d",
"model.layers.44.self_attn.k_proj",
"model.layers.44.self_attn.o_norm",
"model.layers.44.self_attn.o_proj",
"model.layers.44.self_attn.q_conv1d",
"model.layers.44.self_attn.q_proj",
"model.layers.44.self_attn.qkv_proj",
"model.layers.44.self_attn.v_conv1d",
"model.layers.44.self_attn.v_proj",
"model.layers.45.eh_proj",
"model.layers.45.enorm",
"model.layers.45.hnorm",
"model.layers.45.input_layernorm",
"model.layers.45.mlp.gate",
"model.layers.45.mlp.gate.e_score_correction_bias",
"model.layers.45.post_attention_layernorm",
"model.layers.45.self_attn.indexer.index_kpool_compress_ape",
"model.layers.45.self_attn.indexer.index_kpool_compress_gate",
"model.layers.45.self_attn.indexer.k_norm",
"model.layers.45.self_attn.indexer.k_norm.bias",
"model.layers.45.self_attn.indexer.weights_proj",
"model.layers.45.self_attn.indexer.wk",
"model.layers.45.self_attn.indexer.wq_b",
"model.layers.45.self_attn.kv_a_layernorm",
"model.layers.45.self_attn.kv_b_proj",
"model.layers.45.self_attn.q_a_layernorm",
"model.layers.45.shared_head.norm",
"model.layers.5.hc_attn_base",
"model.layers.5.hc_attn_fn",
"model.layers.5.hc_attn_scale",
"model.layers.5.hc_ffn_base",
"model.layers.5.hc_ffn_fn",
"model.layers.5.hc_ffn_scale",
"model.layers.5.input_layernorm",
"model.layers.5.mlp.gate",
"model.layers.5.mlp.gate.e_score_correction_bias",
"model.layers.5.post_attention_layernorm",
"model.layers.5.self_attn.A_log",
"model.layers.5.self_attn.b_proj",
"model.layers.5.self_attn.dt_bias",
"model.layers.5.self_attn.f_a_proj",
"model.layers.5.self_attn.f_b_proj",
"model.layers.5.self_attn.fused_qkvbfg_a_proj",
"model.layers.5.self_attn.g_a_proj",
"model.layers.5.self_attn.g_b_proj",
"model.layers.5.self_attn.k_conv1d",
"model.layers.5.self_attn.k_proj",
"model.layers.5.self_attn.o_norm",
"model.layers.5.self_attn.o_proj",
"model.layers.5.self_attn.q_conv1d",
"model.layers.5.self_attn.q_proj",
"model.layers.5.self_attn.qkv_proj",
"model.layers.5.self_attn.v_conv1d",
"model.layers.5.self_attn.v_proj",
"model.layers.6.hc_attn_base",
"model.layers.6.hc_attn_fn",
"model.layers.6.hc_attn_scale",
"model.layers.6.hc_ffn_base",
"model.layers.6.hc_ffn_fn",
"model.layers.6.hc_ffn_scale",
"model.layers.6.input_layernorm",
"model.layers.6.mlp.gate",
"model.layers.6.mlp.gate.e_score_correction_bias",
"model.layers.6.post_attention_layernorm",
"model.layers.6.self_attn.A_log",
"model.layers.6.self_attn.b_proj",
"model.layers.6.self_attn.dt_bias",
"model.layers.6.self_attn.f_a_proj",
"model.layers.6.self_attn.f_b_proj",
"model.layers.6.self_attn.fused_qkvbfg_a_proj",
"model.layers.6.self_attn.g_a_proj",
"model.layers.6.self_attn.g_b_proj",
"model.layers.6.self_attn.k_conv1d",
"model.layers.6.self_attn.k_proj",
"model.layers.6.self_attn.o_norm",
"model.layers.6.self_attn.o_proj",
"model.layers.6.self_attn.q_conv1d",
"model.layers.6.self_attn.q_proj",
"model.layers.6.self_attn.qkv_proj",
"model.layers.6.self_attn.v_conv1d",
"model.layers.6.self_attn.v_proj",
"model.layers.7.hc_attn_base",
"model.layers.7.hc_attn_fn",
"model.layers.7.hc_attn_scale",
"model.layers.7.hc_ffn_base",
"model.layers.7.hc_ffn_fn",
"model.layers.7.hc_ffn_scale",
"model.layers.7.input_layernorm",
"model.layers.7.mlp.gate",
"model.layers.7.mlp.gate.e_score_correction_bias",
"model.layers.7.post_attention_layernorm",
"model.layers.7.self_attn.indexer.index_kpool_compress_ape",
"model.layers.7.self_attn.indexer.index_kpool_compress_gate",
"model.layers.7.self_attn.indexer.k_norm",
"model.layers.7.self_attn.indexer.k_norm.bias",
"model.layers.7.self_attn.indexer.weights_proj",
"model.layers.7.self_attn.indexer.wk",
"model.layers.7.self_attn.indexer.wq_b",
"model.layers.7.self_attn.kv_a_layernorm",
"model.layers.7.self_attn.kv_b_proj",
"model.layers.7.self_attn.q_a_layernorm",
"model.layers.8.hc_attn_base",
"model.layers.8.hc_attn_fn",
"model.layers.8.hc_attn_scale",
"model.layers.8.hc_ffn_base",
"model.layers.8.hc_ffn_fn",
"model.layers.8.hc_ffn_scale",
"model.layers.8.input_layernorm",
"model.layers.8.mlp.gate",
"model.layers.8.mlp.gate.e_score_correction_bias",
"model.layers.8.post_attention_layernorm",
"model.layers.8.self_attn.A_log",
"model.layers.8.self_attn.b_proj",
"model.layers.8.self_attn.dt_bias",
"model.layers.8.self_attn.f_a_proj",
"model.layers.8.self_attn.f_b_proj",
"model.layers.8.self_attn.fused_qkvbfg_a_proj",
"model.layers.8.self_attn.g_a_proj",
"model.layers.8.self_attn.g_b_proj",
"model.layers.8.self_attn.k_conv1d",
"model.layers.8.self_attn.k_proj",
"model.layers.8.self_attn.o_norm",
"model.layers.8.self_attn.o_proj",
"model.layers.8.self_attn.q_conv1d",
"model.layers.8.self_attn.q_proj",
"model.layers.8.self_attn.qkv_proj",
"model.layers.8.self_attn.v_conv1d",
"model.layers.8.self_attn.v_proj",
"model.layers.9.hc_attn_base",
"model.layers.9.hc_attn_fn",
"model.layers.9.hc_attn_scale",
"model.layers.9.hc_ffn_base",
"model.layers.9.hc_ffn_fn",
"model.layers.9.hc_ffn_scale",
"model.layers.9.input_layernorm",
"model.layers.9.mlp.gate",
"model.layers.9.mlp.gate.e_score_correction_bias",
"model.layers.9.post_attention_layernorm",
"model.layers.9.self_attn.A_log",
"model.layers.9.self_attn.b_proj",
"model.layers.9.self_attn.dt_bias",
"model.layers.9.self_attn.f_a_proj",
"model.layers.9.self_attn.f_b_proj",
"model.layers.9.self_attn.fused_qkvbfg_a_proj",
"model.layers.9.self_attn.g_a_proj",
"model.layers.9.self_attn.g_b_proj",
"model.layers.9.self_attn.k_conv1d",
"model.layers.9.self_attn.k_proj",
"model.layers.9.self_attn.o_norm",
"model.layers.9.self_attn.o_proj",
"model.layers.9.self_attn.q_conv1d",
"model.layers.9.self_attn.q_proj",
"model.layers.9.self_attn.qkv_proj",
"model.layers.9.self_attn.v_conv1d",
"model.layers.9.self_attn.v_proj",
"model.norm",
"model.visual",
"router",
"visual",
"visual.blocks.0.attn.k_norm",
"visual.blocks.0.attn.proj",
"visual.blocks.0.attn.proj.bias",
"visual.blocks.0.attn.q_norm",
"visual.blocks.0.attn.qkv",
"visual.blocks.0.attn.qkv.bias",
"visual.blocks.0.mlp.down_proj",
"visual.blocks.0.mlp.down_proj.bias",
"visual.blocks.0.mlp.gate_proj",
"visual.blocks.0.mlp.gate_proj.bias",
"visual.blocks.0.mlp.up_proj",
"visual.blocks.0.mlp.up_proj.bias",
"visual.blocks.0.norm1",
"visual.blocks.0.norm2",
"visual.blocks.1.attn.k_norm",
"visual.blocks.1.attn.proj",
"visual.blocks.1.attn.proj.bias",
"visual.blocks.1.attn.q_norm",
"visual.blocks.1.attn.qkv",
"visual.blocks.1.attn.qkv.bias",
"visual.blocks.1.mlp.down_proj",
"visual.blocks.1.mlp.down_proj.bias",
"visual.blocks.1.mlp.gate_proj",
"visual.blocks.1.mlp.gate_proj.bias",
"visual.blocks.1.mlp.up_proj",
"visual.blocks.1.mlp.up_proj.bias",
"visual.blocks.1.norm1",
"visual.blocks.1.norm2",
"visual.blocks.10.attn.k_norm",
"visual.blocks.10.attn.proj",
"visual.blocks.10.attn.proj.bias",
"visual.blocks.10.attn.q_norm",
"visual.blocks.10.attn.qkv",
"visual.blocks.10.attn.qkv.bias",
"visual.blocks.10.mlp.down_proj",
"visual.blocks.10.mlp.down_proj.bias",
"visual.blocks.10.mlp.gate_proj",
"visual.blocks.10.mlp.gate_proj.bias",
"visual.blocks.10.mlp.up_proj",
"visual.blocks.10.mlp.up_proj.bias",
"visual.blocks.10.norm1",
"visual.blocks.10.norm2",
"visual.blocks.11.attn.k_norm",
"visual.blocks.11.attn.proj",
"visual.blocks.11.attn.proj.bias",
"visual.blocks.11.attn.q_norm",
"visual.blocks.11.attn.qkv",
"visual.blocks.11.attn.qkv.bias",
"visual.blocks.11.mlp.down_proj",
"visual.blocks.11.mlp.down_proj.bias",
"visual.blocks.11.mlp.gate_proj",
"visual.blocks.11.mlp.gate_proj.bias",
"visual.blocks.11.mlp.up_proj",
"visual.blocks.11.mlp.up_proj.bias",
"visual.blocks.11.norm1",
"visual.blocks.11.norm2",
"visual.blocks.12.attn.k_norm",
"visual.blocks.12.attn.proj",
"visual.blocks.12.attn.proj.bias",
"visual.blocks.12.attn.q_norm",
"visual.blocks.12.attn.qkv",
"visual.blocks.12.attn.qkv.bias",
"visual.blocks.12.mlp.down_proj",
"visual.blocks.12.mlp.down_proj.bias",
"visual.blocks.12.mlp.gate_proj",
"visual.blocks.12.mlp.gate_proj.bias",
"visual.blocks.12.mlp.up_proj",
"visual.blocks.12.mlp.up_proj.bias",
"visual.blocks.12.norm1",
"visual.blocks.12.norm2",
"visual.blocks.13.attn.k_norm",
"visual.blocks.13.attn.proj",
"visual.blocks.13.attn.proj.bias",
"visual.blocks.13.attn.q_norm",
"visual.blocks.13.attn.qkv",
"visual.blocks.13.attn.qkv.bias",
"visual.blocks.13.mlp.down_proj",
"visual.blocks.13.mlp.down_proj.bias",
"visual.blocks.13.mlp.gate_proj",
"visual.blocks.13.mlp.gate_proj.bias",
"visual.blocks.13.mlp.up_proj",
"visual.blocks.13.mlp.up_proj.bias",
"visual.blocks.13.norm1",
"visual.blocks.13.norm2",
"visual.blocks.14.attn.k_norm",
"visual.blocks.14.attn.proj",
"visual.blocks.14.attn.proj.bias",
"visual.blocks.14.attn.q_norm",
"visual.blocks.14.attn.qkv",
"visual.blocks.14.attn.qkv.bias",
"visual.blocks.14.mlp.down_proj",
"visual.blocks.14.mlp.down_proj.bias",
"visual.blocks.14.mlp.gate_proj",
"visual.blocks.14.mlp.gate_proj.bias",
"visual.blocks.14.mlp.up_proj",
"visual.blocks.14.mlp.up_proj.bias",
"visual.blocks.14.norm1",
"visual.blocks.14.norm2",
"visual.blocks.15.attn.k_norm",
"visual.blocks.15.attn.proj",
"visual.blocks.15.attn.proj.bias",
"visual.blocks.15.attn.q_norm",
"visual.blocks.15.attn.qkv",
"visual.blocks.15.attn.qkv.bias",
"visual.blocks.15.mlp.down_proj",
"visual.blocks.15.mlp.down_proj.bias",
"visual.blocks.15.mlp.gate_proj",
"visual.blocks.15.mlp.gate_proj.bias",
"visual.blocks.15.mlp.up_proj",
"visual.blocks.15.mlp.up_proj.bias",
"visual.blocks.15.norm1",
"visual.blocks.15.norm2",
"visual.blocks.16.attn.k_norm",
"visual.blocks.16.attn.proj",
"visual.blocks.16.attn.proj.bias",
"visual.blocks.16.attn.q_norm",
"visual.blocks.16.attn.qkv",
"visual.blocks.16.attn.qkv.bias",
"visual.blocks.16.mlp.down_proj",
"visual.blocks.16.mlp.down_proj.bias",
"visual.blocks.16.mlp.gate_proj",
"visual.blocks.16.mlp.gate_proj.bias",
"visual.blocks.16.mlp.up_proj",
"visual.blocks.16.mlp.up_proj.bias",
"visual.blocks.16.norm1",
"visual.blocks.16.norm2",
"visual.blocks.17.attn.k_norm",
"visual.blocks.17.attn.proj",
"visual.blocks.17.attn.proj.bias",
"visual.blocks.17.attn.q_norm",
"visual.blocks.17.attn.qkv",
"visual.blocks.17.attn.qkv.bias",
"visual.blocks.17.mlp.down_proj",
"visual.blocks.17.mlp.down_proj.bias",
"visual.blocks.17.mlp.gate_proj",
"visual.blocks.17.mlp.gate_proj.bias",
"visual.blocks.17.mlp.up_proj",
"visual.blocks.17.mlp.up_proj.bias",
"visual.blocks.17.norm1",
"visual.blocks.17.norm2",
"visual.blocks.18.attn.k_norm",
"visual.blocks.18.attn.proj",
"visual.blocks.18.attn.proj.bias",
"visual.blocks.18.attn.q_norm",
"visual.blocks.18.attn.qkv",
"visual.blocks.18.attn.qkv.bias",
"visual.blocks.18.mlp.down_proj",
"visual.blocks.18.mlp.down_proj.bias",
"visual.blocks.18.mlp.gate_proj",
"visual.blocks.18.mlp.gate_proj.bias",
"visual.blocks.18.mlp.up_proj",
"visual.blocks.18.mlp.up_proj.bias",
"visual.blocks.18.norm1",
"visual.blocks.18.norm2",
"visual.blocks.19.attn.k_norm",
"visual.blocks.19.attn.proj",
"visual.blocks.19.attn.proj.bias",
"visual.blocks.19.attn.q_norm",
"visual.blocks.19.attn.qkv",
"visual.blocks.19.attn.qkv.bias",
"visual.blocks.19.mlp.down_proj",
"visual.blocks.19.mlp.down_proj.bias",
"visual.blocks.19.mlp.gate_proj",
"visual.blocks.19.mlp.gate_proj.bias",
"visual.blocks.19.mlp.up_proj",
"visual.blocks.19.mlp.up_proj.bias",
"visual.blocks.19.norm1",
"visual.blocks.19.norm2",
"visual.blocks.2.attn.k_norm",
"visual.blocks.2.attn.proj",
"visual.blocks.2.attn.proj.bias",
"visual.blocks.2.attn.q_norm",
"visual.blocks.2.attn.qkv",
"visual.blocks.2.attn.qkv.bias",
"visual.blocks.2.mlp.down_proj",
"visual.blocks.2.mlp.down_proj.bias",
"visual.blocks.2.mlp.gate_proj",
"visual.blocks.2.mlp.gate_proj.bias",
"visual.blocks.2.mlp.up_proj",
"visual.blocks.2.mlp.up_proj.bias",
"visual.blocks.2.norm1",
"visual.blocks.2.norm2",
"visual.blocks.20.attn.k_norm",
"visual.blocks.20.attn.proj",
"visual.blocks.20.attn.proj.bias",
"visual.blocks.20.attn.q_norm",
"visual.blocks.20.attn.qkv",
"visual.blocks.20.attn.qkv.bias",
"visual.blocks.20.mlp.down_proj",
"visual.blocks.20.mlp.down_proj.bias",
"visual.blocks.20.mlp.gate_proj",
"visual.blocks.20.mlp.gate_proj.bias",
"visual.blocks.20.mlp.up_proj",
"visual.blocks.20.mlp.up_proj.bias",
"visual.blocks.20.norm1",
"visual.blocks.20.norm2",
"visual.blocks.21.attn.k_norm",
"visual.blocks.21.attn.proj",
"visual.blocks.21.attn.proj.bias",
"visual.blocks.21.attn.q_norm",
"visual.blocks.21.attn.qkv",
"visual.blocks.21.attn.qkv.bias",
"visual.blocks.21.mlp.down_proj",
"visual.blocks.21.mlp.down_proj.bias",
"visual.blocks.21.mlp.gate_proj",
"visual.blocks.21.mlp.gate_proj.bias",
"visual.blocks.21.mlp.up_proj",
"visual.blocks.21.mlp.up_proj.bias",
"visual.blocks.21.norm1",
"visual.blocks.21.norm2",
"visual.blocks.22.attn.k_norm",
"visual.blocks.22.attn.proj",
"visual.blocks.22.attn.proj.bias",
"visual.blocks.22.attn.q_norm",
"visual.blocks.22.attn.qkv",
"visual.blocks.22.attn.qkv.bias",
"visual.blocks.22.mlp.down_proj",
"visual.blocks.22.mlp.down_proj.bias",
"visual.blocks.22.mlp.gate_proj",
"visual.blocks.22.mlp.gate_proj.bias",
"visual.blocks.22.mlp.up_proj",
"visual.blocks.22.mlp.up_proj.bias",
"visual.blocks.22.norm1",
"visual.blocks.22.norm2",
"visual.blocks.23.attn.k_norm",
"visual.blocks.23.attn.proj",
"visual.blocks.23.attn.proj.bias",
"visual.blocks.23.attn.q_norm",
"visual.blocks.23.attn.qkv",
"visual.blocks.23.attn.qkv.bias",
"visual.blocks.23.mlp.down_proj",
"visual.blocks.23.mlp.down_proj.bias",
"visual.blocks.23.mlp.gate_proj",
"visual.blocks.23.mlp.gate_proj.bias",
"visual.blocks.23.mlp.up_proj",
"visual.blocks.23.mlp.up_proj.bias",
"visual.blocks.23.norm1",
"visual.blocks.23.norm2",
"visual.blocks.3.attn.k_norm",
"visual.blocks.3.attn.proj",
"visual.blocks.3.attn.proj.bias",
"visual.blocks.3.attn.q_norm",
"visual.blocks.3.attn.qkv",
"visual.blocks.3.attn.qkv.bias",
"visual.blocks.3.mlp.down_proj",
"visual.blocks.3.mlp.down_proj.bias",
"visual.blocks.3.mlp.gate_proj",
"visual.blocks.3.mlp.gate_proj.bias",
"visual.blocks.3.mlp.up_proj",
"visual.blocks.3.mlp.up_proj.bias",
"visual.blocks.3.norm1",
"visual.blocks.3.norm2",
"visual.blocks.4.attn.k_norm",
"visual.blocks.4.attn.proj",
"visual.blocks.4.attn.proj.bias",
"visual.blocks.4.attn.q_norm",
"visual.blocks.4.attn.qkv",
"visual.blocks.4.attn.qkv.bias",
"visual.blocks.4.mlp.down_proj",
"visual.blocks.4.mlp.down_proj.bias",
"visual.blocks.4.mlp.gate_proj",
"visual.blocks.4.mlp.gate_proj.bias",
"visual.blocks.4.mlp.up_proj",
"visual.blocks.4.mlp.up_proj.bias",
"visual.blocks.4.norm1",
"visual.blocks.4.norm2",
"visual.blocks.5.attn.k_norm",
"visual.blocks.5.attn.proj",
"visual.blocks.5.attn.proj.bias",
"visual.blocks.5.attn.q_norm",
"visual.blocks.5.attn.qkv",
"visual.blocks.5.attn.qkv.bias",
"visual.blocks.5.mlp.down_proj",
"visual.blocks.5.mlp.down_proj.bias",
"visual.blocks.5.mlp.gate_proj",
"visual.blocks.5.mlp.gate_proj.bias",
"visual.blocks.5.mlp.up_proj",
"visual.blocks.5.mlp.up_proj.bias",
"visual.blocks.5.norm1",
"visual.blocks.5.norm2",
"visual.blocks.6.attn.k_norm",
"visual.blocks.6.attn.proj",
"visual.blocks.6.attn.proj.bias",
"visual.blocks.6.attn.q_norm",
"visual.blocks.6.attn.qkv",
"visual.blocks.6.attn.qkv.bias",
"visual.blocks.6.mlp.down_proj",
"visual.blocks.6.mlp.down_proj.bias",
"visual.blocks.6.mlp.gate_proj",
"visual.blocks.6.mlp.gate_proj.bias",
"visual.blocks.6.mlp.up_proj",
"visual.blocks.6.mlp.up_proj.bias",
"visual.blocks.6.norm1",
"visual.blocks.6.norm2",
"visual.blocks.7.attn.k_norm",
"visual.blocks.7.attn.proj",
"visual.blocks.7.attn.proj.bias",
"visual.blocks.7.attn.q_norm",
"visual.blocks.7.attn.qkv",
"visual.blocks.7.attn.qkv.bias",
"visual.blocks.7.mlp.down_proj",
"visual.blocks.7.mlp.down_proj.bias",
"visual.blocks.7.mlp.gate_proj",
"visual.blocks.7.mlp.gate_proj.bias",
"visual.blocks.7.mlp.up_proj",
"visual.blocks.7.mlp.up_proj.bias",
"visual.blocks.7.norm1",
"visual.blocks.7.norm2",
"visual.blocks.8.attn.k_norm",
"visual.blocks.8.attn.proj",
"visual.blocks.8.attn.proj.bias",
"visual.blocks.8.attn.q_norm",
"visual.blocks.8.attn.qkv",
"visual.blocks.8.attn.qkv.bias",
"visual.blocks.8.mlp.down_proj",
"visual.blocks.8.mlp.down_proj.bias",
"visual.blocks.8.mlp.gate_proj",
"visual.blocks.8.mlp.gate_proj.bias",
"visual.blocks.8.mlp.up_proj",
"visual.blocks.8.mlp.up_proj.bias",
"visual.blocks.8.norm1",
"visual.blocks.8.norm2",
"visual.blocks.9.attn.k_norm",
"visual.blocks.9.attn.proj",
"visual.blocks.9.attn.proj.bias",
"visual.blocks.9.attn.q_norm",
"visual.blocks.9.attn.qkv",
"visual.blocks.9.attn.qkv.bias",
"visual.blocks.9.mlp.down_proj",
"visual.blocks.9.mlp.down_proj.bias",
"visual.blocks.9.mlp.gate_proj",
"visual.blocks.9.mlp.gate_proj.bias",
"visual.blocks.9.mlp.up_proj",
"visual.blocks.9.mlp.up_proj.bias",
"visual.blocks.9.norm1",
"visual.blocks.9.norm2",
"visual.downsample",
"visual.downsample.bias",
"visual.merger.down_proj",
"visual.merger.gate_proj",
"visual.merger.post_projection_norm",
"visual.merger.post_projection_norm.bias",
"visual.merger.proj",
"visual.merger.up_proj",
"visual.patch_embed.proj",
"visual.patch_embed.proj.bias",
"visual.post_layernorm",
"weights_proj"
],
"quant_method": "fp8"
},
"tokenizer_config": {
"eos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>"
}
},
"createdAt": "2026-08-26T21:09:20.000Z",
"disabled": false,
"downloads": 49224,
"gated": false,
"id": "dealignai/GLM-5.3-Flash-UNCENSORED-FP8",
"lastModified": "2026-09-19T16:32:29.000Z",
"likes": 126,
"model-index": null,
"modelId": "dealignai/GLM-5.3-Flash-UNCENSORED-FP8",
"private": false,
"safetensors": {
"parameters": {
"BF16": 6926096640,
"F32": 295518,
"F8_E4M3": 314396639232
},
"total": 321323031390
},
"sha": "d5822b068da8ddb301665b48c58718e6e18a2c3a",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "dealign_logo.png"
},
{
"rfilename": "dealign_mascot.png"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "model-00001-of-00062.safetensors"
},
{
"rfilename": "model-00002-of-00062.safetensors"
},
{
"rfilename": "model-00003-of-00062.safetensors"
},
{
"rfilename": "model-00004-of-00062.safetensors"
},
{
"rfilename": "model-00005-of-00062.safetensors"
},
{
"rfilename": "model-00006-of-00062.safetensors"
},
{
"rfilename": "model-00007-of-00062.safetensors"
},
{
"rfilename": "model-00008-of-00062.safetensors"
},
{
"rfilename": "model-00009-of-00062.safetensors"
},
{
"rfilename": "model-00010-of-00062.safetensors"
},
{
"rfilename": "model-00011-of-00062.safetensors"
},
{
"rfilename": "model-00012-of-00062.safetensors"
},
{
"rfilename": "model-00013-of-00062.safetensors"
},
{
"rfilename": "model-00014-of-00062.safetensors"
},
{
"rfilename": "model-00015-of-00062.safetensors"
},
{
"rfilename": "model-00016-of-00062.safetensors"
},
{
"rfilename": "model-00017-of-00062.safetensors"
},
{
"rfilename": "model-00018-of-00062.safetensors"
},
{
"rfilename": "model-00019-of-00062.safetensors"
},
{
"rfilename": "model-00020-of-00062.safetensors"
},
{
"rfilename": "model-00021-of-00062.safetensors"
},
{
"rfilename": "model-00022-of-00062.safetensors"
},
{
"rfilename": "model-00023-of-00062.safetensors"
},
{
"rfilename": "model-00024-of-00062.safetensors"
},
{
"rfilename": "model-00025-of-00062.safetensors"
},
{
"rfilename": "model-00026-of-00062.safetensors"
},
{
"rfilename": "model-00027-of-00062.safetensors"
},
{
"rfilename": "model-00028-of-00062.safetensors"
},
{
"rfilename": "model-00029-of-00062.safetensors"
},
{
"rfilename": "model-00030-of-00062.safetensors"
},
{
"rfilename": "model-00031-of-00062.safetensors"
},
{
"rfilename": "model-00032-of-00062.safetensors"
},
{
"rfilename": "model-00033-of-00062.safetensors"
},
{
"rfilename": "model-00034-of-00062.safetensors"
},
{
"rfilename": "model-00035-of-00062.safetensors"
},
{
"rfilename": "model-00036-of-00062.safetensors"
},
{
"rfilename": "model-00037-of-00062.safetensors"
},
{
"rfilename": "model-00038-of-00062.safetensors"
},
{
"rfilename": "model-00039-of-00062.safetensors"
},
{
"rfilename": "model-00040-of-00062.safetensors"
},
{
"rfilename": "model-00041-of-00062.safetensors"
},
{
"rfilename": "model-00042-of-00062.safetensors"
},
{
"rfilename": "model-00043-of-00062.safetensors"
},
{
"rfilename": "model-00044-of-00062.safetensors"
},
{
"rfilename": "model-00045-of-00062.safetensors"
},
{
"rfilename": "model-00046-of-00062.safetensors"
},
{
"rfilename": "model-00047-of-00062.safetensors"
},
{
"rfilename": "model-00048-of-00062.safetensors"
},
{
"rfilename": "model-00049-of-00062.safetensors"
},
{
"rfilename": "model-00050-of-00062.safetensors"
},
{
"rfilename": "model-00051-of-00062.safetensors"
},
{
"rfilename": "model-00052-of-00062.safetensors"
},
{
"rfilename": "model-00053-of-00062.safetensors"
},
{
"rfilename": "model-00054-of-00062.safetensors"
},
{
"rfilename": "model-00055-of-00062.safetensors"
},
{
"rfilename": "model-00056-of-00062.safetensors"
},
{
"rfilename": "model-00057-of-00062.safetensors"
},
{
"rfilename": "model-00058-of-00062.safetensors"
},
{
"rfilename": "model-00059-of-00062.safetensors"
},
{
"rfilename": "model-00060-of-00062.safetensors"
},
{
"rfilename": "model-00061-of-00062.safetensors"
},
{
"rfilename": "model-00062-of-00062.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "processor_config.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
}
],
"spaces": [
"tardellirs/model-pulse",
"aquanode/gpu-vram-calculator"
],
"tags": [
"safetensors",
"glm5_next",
"abliterated",
"uncensored",
"crack",
"glm",
"moe",
"fp8",
"vision",
"mtp",
"en",
"base_model:zai-org/GLM-5.3-Flash",
"base_model:quantized:zai-org/GLM-5.3-Flash",
"license:mit",
"region:us"
],
"usedStorage": 505375369250
} | ||||||||
| licence | mitreceipt
What the source handed over{
"_asked": "dealignai/GLM-5.3-Flash-UNCENSORED-FP8",
"_id": "6a8f5600e8e799f3299d529f",
"author": "dealignai",
"cardData": {
"base_model": [
"zai-org/GLM-5.3-Flash"
],
"language": [
"en"
],
"license": "mit",
"tags": [
"abliterated",
"uncensored",
"crack",
"glm",
"moe",
"fp8",
"vision",
"mtp"
],
"thumbnail": "dealign_mascot.png"
},
"config": {
"architectures": [
"Glm5NextForConditionalGeneration"
],
"chat_template_jinja": "[gMASK]<sop>\n{%- set effective_reasoning_effort = reasoning_effort if reasoning_effort is defined and reasoning_effort in ['low', 'high'] else 'max' -%}\n{%- if effective_reasoning_effort is not none -%}<|system|>Reasoning Effort: {{ effective_reasoning_effort | capitalize }}{%- endif -%}\n{%- set clear_thinking = clear_thinking if clear_thinking is defined else true -%}\n{%- if tools -%}\n{%- macro tool_to_json(tool) -%}\n {%- set ns_tool = namespace(first=true) -%}\n {{ '{' -}}\n {%- for k, v in tool.items() -%}\n {%- if k != 'defer_loading' and k != 'strict' -%}\n {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}\n {%- set ns_tool.first = false -%}\n \"{{ k }}\": {{ v | tojson(ensure_ascii=False) }}\n {%- endif -%}\n {%- endfor -%}\n {{- '}' -}}\n{%- endmacro -%}\n{%- macro tool_references_to_response(refs) -%}\n {{- '<tool_response><tools>\\n' -}}\n {%- for tr in refs -%}\n {%- for tool in tools -%}\n {%- if 'function' in tool -%}\n {%- set tool = tool['function'] -%}\n {%- endif -%}\n {%- if tool.name == tr.name -%}\n {{- tool_to_json(tool) + '\\n' -}}\n {%- endif -%}\n {%- endfor -%}\n {%- endfor -%}\n {{- '</tools></tool_response>' -}}\n{%- endmacro -%}\n<|system|>\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{% for tool in tools %}\n{%- if 'function' in tool -%}\n {%- set tool = tool['function'] -%}\n{%- endif -%}\n{% if tool.defer_loading is not defined or not tool.defer_loading %}\n{{ tool_to_json(tool) }}\n{% endif %}\n{% endfor %}\n</tools>\n\nFor each function call, output the function name and arguments within the following XML format:\n<tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}\n{%- macro emit_image() -%}<|begin_of_image|><|image|><|end_of_image|>{%- endmacro -%}\n{%- macro emit_video() -%}<|begin_of_video|><|video|><|end_of_video|>{%- endmacro -%}\n{%- macro emit_audio() -%}<|begin_of_audio|><|end_of_audio|>{%- endmacro -%}\n{%- macro visible_text(content) -%}\n {%- if content is string -%}\n {{- content -}}\n {%- elif content is iterable and content is not mapping -%}\n {%- for item in content -%}\n {%- if item is mapping and item.type == 'text' -%}\n {{- item.text -}}\n {%- elif item is string -%}\n {{- item -}}\n {%- elif item is mapping and item.type in ['image', 'image_url'] -%}\n {{- emit_image() -}}\n {%- elif item is mapping and item.type in ['video', 'video_url'] -%}\n {{- emit_video() -}}\n {%- elif item is mapping and item.type in ['audio', 'audio_url', 'input_audio'] -%}\n {{- emit_audio() -}}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{- content }}\n {%- endif -%}\n{%- endmacro -%}\n{%- macro tool_response(text) -%}\n{{- '<tool_response>' + text + '</tool_response>' -}}\n{%- endmacro -%}\n{%- macro render_tool_response(m) -%}\n{%- if m.content is string -%}\n {{- tool_response(m.content) -}}\n{%- elif m.content and m.content is not mapping and m.content.0.type == \"tool_reference\" -%}\n {{- tool_references_to_response(m.content) -}}\n{%- elif is_list_of_outputs(m) -%}\n {%- for tr in m.content -%}\n {%- if tr.output is iterable and tr.output is not string and tr.output is not mapping and tr.output and tr.output.0.type == \"tool_reference\" -%}\n {{- tool_references_to_response(tr.output) -}}\n {%- else -%}\n {{- tool_response(visible_text(tr.output)) -}}\n {%- endif -%}\n {%- endfor -%}\n{%- else -%}\n {{- tool_response(visible_text(m.content)) -}}\n{%- endif -%}\n{%- endmacro -%}\n{%- macro id_of(obj) -%}\n {%- if obj.tool_call_id -%}\n {{- obj.tool_call_id -}}\n {%- elif obj.id -%}\n {{- obj.id -}}\n {%- endif -%}\n{%- endmacro -%}\n{%- macro is_list_of_outputs(m) -%}\n {%- if m.content and m.content.0.output is defined -%}1{%- endif -%}\n{%- endmacro -%}\n{%- macro has_dup_tool_result_id(lo, hi, target) -%}\n {%- set ns_cnt = namespace(n=0) -%}\n {%- for k in range(lo, hi + 1) -%}\n {%- set m = messages[k] -%}\n {%- if is_list_of_outputs(m) -%}\n {%- for entry in m.content -%}\n {%- if id_of(entry) == target -%}\n {%- set ns_cnt.n = ns_cnt.n + 1 -%}\n {%- endif -%}\n {%- endfor -%}\n {%- elif id_of(m) == target -%}\n {%- set ns_cnt.n = ns_cnt.n + 1 -%}\n {%- endif -%}\n {%- if ns_cnt.n > 1 -%}{%- break -%}{%- endif -%}\n {%- endfor -%}\n {%- if ns_cnt.n > 1 -%}1{%- endif -%}\n{%- endmacro -%}\n{%- macro tc_id_exists(tcs, target) -%}\n {%- set ns_f = namespace(found=false) -%}\n {%- for tc in tcs -%}\n {%- if id_of(tc) == target -%}\n {%- set ns_f.found = true -%}\n {%- break -%}\n {%- endif -%}\n {%- endfor -%}\n {%- if ns_f.found -%}1{%- endif -%}\n{%- endmacro -%}\n{%- set ns = namespace(last_user_index=-1) -%}\n{%- for m in messages %}\n {%- if m.role == 'user' %}\n {%- set ns.last_user_index = loop.index0 -%}\n {%- endif %}\n{%- endfor %}\n{%- for m in messages -%}\n{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}\n{%- elif m.role == 'assistant' -%}\n<|assistant|>\n{%- set content = visible_text(m.content) %}\n{%- if m.reasoning_content is string %}\n {%- set reasoning_content = m.reasoning_content %}\n{%- elif '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}\n {%- set content = content.split('</think>')[-1] %}\n{%- endif %}\n{%- if (not clear_thinking or loop.index0 > ns.last_user_index) and reasoning_content is defined -%}\n{{ '<think>' + reasoning_content + '</think>'}}\n{%- else -%}\n{{ '<think></think>' }}\n{%- endif -%}\n{%- if content.strip() -%}\n{{ content.strip() }}\n{%- endif -%}\n{% if m.tool_calls %}\n{% for tc in m.tool_calls %}\n{%- if tc.function %}\n {%- set tc = tc.function %}\n{%- endif %}\n{{- '<tool_call>' + tc.name -}}\n{% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}\n{% endif %}\n{%- elif m.role == 'tool' -%}\n{%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|observation|>' -}}\n {%- set block_start = loop.index0 -%}\n {%- set ns_blk = namespace(end=block_start) -%}\n {%- for j in range(block_start, messages|length) -%}\n {%- if messages[j].role == 'tool' -%}\n {%- set ns_blk.end = j -%}\n {%- else -%}\n {%- break -%}\n {%- endif -%}\n {%- endfor -%}\n {%- set ns_a = namespace(tool_calls=none) -%}\n {%- if block_start > 0 and messages[block_start - 1].role == 'assistant' and messages[block_start - 1].tool_calls -%}\n {%- set ns_a.tool_calls = messages[block_start - 1].tool_calls -%}\n {%- endif -%}\n {%- set ns_chk = namespace(can_sort=true) -%}\n {%- if not ns_a.tool_calls -%}\n {%- set ns_chk.can_sort = false -%}\n {%- else -%}\n {%- for k in range(block_start, ns_blk.end + 1) -%}\n {%- set m = messages[k] -%}\n {%- if is_list_of_outputs(m) -%}\n {%- for entry in m.content -%}\n {%- set eid = id_of(entry) -%}\n {%- if not eid -%}\n {%- set ns_chk.can_sort = false -%}\n {%- elif has_dup_tool_result_id(block_start, ns_blk.end, eid) -%}\n {%- set ns_chk.can_sort = false -%}\n {%- elif not tc_id_exists(ns_a.tool_calls, eid) -%}\n {%- set ns_chk.can_sort = false -%}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {%- set tk_id = id_of(m) -%}\n {%- if not tk_id -%}\n {%- set ns_chk.can_sort = false -%}\n {%- elif has_dup_tool_result_id(block_start, ns_blk.end, tk_id) -%}\n {%- set ns_chk.can_sort = false -%}\n {%- elif not tc_id_exists(ns_a.tool_calls, tk_id) -%}\n {%- set ns_chk.can_sort = false -%}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n {%- for i in range(ns_a.tool_calls | length) -%}\n {%- set tc_id = id_of(ns_a.tool_calls[i]) -%}\n {%- if not tc_id -%}\n {%- set ns_chk.can_sort = false -%}\n {%- endif -%}\n {%- for j in range(i + 1, ns_a.tool_calls | length) -%}\n {%- if id_of(ns_a.tool_calls[j]) == tc_id -%}\n {%- set ns_chk.can_sort = false -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endfor -%}\n {%- endif -%}\n {%- if ns_chk.can_sort -%}\n {%- for tc in ns_a.tool_calls -%}\n {%- set tc_id = id_of(tc) -%}\n {%- for k in range(block_start, ns_blk.end + 1) -%}\n {%- set m = messages[k] -%}\n {%- if is_list_of_outputs(m) -%}\n {%- for entry in m.content -%}\n {%- set eid = id_of(entry) -%}\n {%- if eid == tc_id -%}\n {%- if entry.output is iterable and entry.output is not string and entry.output is not mapping and entry.output and entry.output.0.type == \"tool_reference\" -%}\n {{- tool_references_to_response(entry.output) -}}\n {%- else -%}\n {{- tool_response(visible_text(entry.output)) -}}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n{%- else -%}\n {%- set tk_id = id_of(m) -%}\n {%- if tk_id == tc_id -%}\n {{- render_tool_response(m) -}}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endfor -%}\n {%- else -%}\n {%- for k in range(block_start, ns_blk.end + 1) -%}\n {{- render_tool_response(messages[k]) -}}\n {%- endfor -%}\n {%- endif -%}\n{% endif -%}\n{%- elif m.role == 'system' -%}\n<|system|>{{ visible_text(m.content) }}\n{%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n <|assistant|>{{- '<think>' -}}\n{%- endif -%}\n",
"model_type": "glm5_next",
"quantization_config": {
"modules_to_not_convert": [
"attn_mha",
"attn_mqa",
"dt_bias",
"hyper_connection",
"lm_head",
"mapping_proj",
"model.embed_tokens",
"model.layers.0.hc_attn_base",
"model.layers.0.hc_attn_fn",
"model.layers.0.hc_attn_scale",
"model.layers.0.hc_ffn_base",
"model.layers.0.hc_ffn_fn",
"model.layers.0.hc_ffn_scale",
"model.layers.0.input_layernorm",
"model.layers.0.post_attention_layernorm",
"model.layers.0.self_attn.A_log",
"model.layers.0.self_attn.b_proj",
"model.layers.0.self_attn.dt_bias",
"model.layers.0.self_attn.f_a_proj",
"model.layers.0.self_attn.f_b_proj",
"model.layers.0.self_attn.fused_qkvbfg_a_proj",
"model.layers.0.self_attn.g_a_proj",
"model.layers.0.self_attn.g_b_proj",
"model.layers.0.self_attn.k_conv1d",
"model.layers.0.self_attn.k_proj",
"model.layers.0.self_attn.o_norm",
"model.layers.0.self_attn.o_proj",
"model.layers.0.self_attn.q_conv1d",
"model.layers.0.self_attn.q_proj",
"model.layers.0.self_attn.qkv_proj",
"model.layers.0.self_attn.v_conv1d",
"model.layers.0.self_attn.v_proj",
"model.layers.1.hc_attn_base",
"model.layers.1.hc_attn_fn",
"model.layers.1.hc_attn_scale",
"model.layers.1.hc_ffn_base",
"model.layers.1.hc_ffn_fn",
"model.layers.1.hc_ffn_scale",
"model.layers.1.input_layernorm",
"model.layers.1.post_attention_layernorm",
"model.layers.1.self_attn.A_log",
"model.layers.1.self_attn.b_proj",
"model.layers.1.self_attn.dt_bias",
"model.layers.1.self_attn.f_a_proj",
"model.layers.1.self_attn.f_b_proj",
"model.layers.1.self_attn.fused_qkvbfg_a_proj",
"model.layers.1.self_attn.g_a_proj",
"model.layers.1.self_attn.g_b_proj",
"model.layers.1.self_attn.k_conv1d",
"model.layers.1.self_attn.k_proj",
"model.layers.1.self_attn.o_norm",
"model.layers.1.self_attn.o_proj",
"model.layers.1.self_attn.q_conv1d",
"model.layers.1.self_attn.q_proj",
"model.layers.1.self_attn.qkv_proj",
"model.layers.1.self_attn.v_conv1d",
"model.layers.1.self_attn.v_proj",
"model.layers.10.hc_attn_base",
"model.layers.10.hc_attn_fn",
"model.layers.10.hc_attn_scale",
"model.layers.10.hc_ffn_base",
"model.layers.10.hc_ffn_fn",
"model.layers.10.hc_ffn_scale",
"model.layers.10.input_layernorm",
"model.layers.10.mlp.gate",
"model.layers.10.mlp.gate.e_score_correction_bias",
"model.layers.10.post_attention_layernorm",
"model.layers.10.self_attn.A_log",
"model.layers.10.self_attn.b_proj",
"model.layers.10.self_attn.dt_bias",
"model.layers.10.self_attn.f_a_proj",
"model.layers.10.self_attn.f_b_proj",
"model.layers.10.self_attn.fused_qkvbfg_a_proj",
"model.layers.10.self_attn.g_a_proj",
"model.layers.10.self_attn.g_b_proj",
"model.layers.10.self_attn.k_conv1d",
"model.layers.10.self_attn.k_proj",
"model.layers.10.self_attn.o_norm",
"model.layers.10.self_attn.o_proj",
"model.layers.10.self_attn.q_conv1d",
"model.layers.10.self_attn.q_proj",
"model.layers.10.self_attn.qkv_proj",
"model.layers.10.self_attn.v_conv1d",
"model.layers.10.self_attn.v_proj",
"model.layers.11.hc_attn_base",
"model.layers.11.hc_attn_fn",
"model.layers.11.hc_attn_scale",
"model.layers.11.hc_ffn_base",
"model.layers.11.hc_ffn_fn",
"model.layers.11.hc_ffn_scale",
"model.layers.11.input_layernorm",
"model.layers.11.mlp.gate",
"model.layers.11.mlp.gate.e_score_correction_bias",
"model.layers.11.post_attention_layernorm",
"model.layers.11.self_attn.indexer.index_kpool_compress_ape",
"model.layers.11.self_attn.indexer.index_kpool_compress_gate",
"model.layers.11.self_attn.indexer.k_norm",
"model.layers.11.self_attn.indexer.k_norm.bias",
"model.layers.11.self_attn.indexer.weights_proj",
"model.layers.11.self_attn.indexer.wk",
"model.layers.11.self_attn.indexer.wq_b",
"model.layers.11.self_attn.kv_a_layernorm",
"model.layers.11.self_attn.kv_b_proj",
"model.layers.11.self_attn.q_a_layernorm",
"model.layers.12.hc_attn_base",
"model.layers.12.hc_attn_fn",
"model.layers.12.hc_attn_scale",
"model.layers.12.hc_ffn_base",
"model.layers.12.hc_ffn_fn",
"model.layers.12.hc_ffn_scale",
"model.layers.12.input_layernorm",
"model.layers.12.mlp.gate",
"model.layers.12.mlp.gate.e_score_correction_bias",
"model.layers.12.post_attention_layernorm",
"model.layers.12.self_attn.A_log",
"model.layers.12.self_attn.b_proj",
"model.layers.12.self_attn.dt_bias",
"model.layers.12.self_attn.f_a_proj",
"model.layers.12.self_attn.f_b_proj",
"model.layers.12.self_attn.fused_qkvbfg_a_proj",
"model.layers.12.self_attn.g_a_proj",
"model.layers.12.self_attn.g_b_proj",
"model.layers.12.self_attn.k_conv1d",
"model.layers.12.self_attn.k_proj",
"model.layers.12.self_attn.o_norm",
"model.layers.12.self_attn.o_proj",
"model.layers.12.self_attn.q_conv1d",
"model.layers.12.self_attn.q_proj",
"model.layers.12.self_attn.qkv_proj",
"model.layers.12.self_attn.v_conv1d",
"model.layers.12.self_attn.v_proj",
"model.layers.13.hc_attn_base",
"model.layers.13.hc_attn_fn",
"model.layers.13.hc_attn_scale",
"model.layers.13.hc_ffn_base",
"model.layers.13.hc_ffn_fn",
"model.layers.13.hc_ffn_scale",
"model.layers.13.input_layernorm",
"model.layers.13.mlp.gate",
"model.layers.13.mlp.gate.e_score_correction_bias",
"model.layers.13.post_attention_layernorm",
"model.layers.13.self_attn.A_log",
"model.layers.13.self_attn.b_proj",
"model.layers.13.self_attn.dt_bias",
"model.layers.13.self_attn.f_a_proj",
"model.layers.13.self_attn.f_b_proj",
"model.layers.13.self_attn.fused_qkvbfg_a_proj",
"model.layers.13.self_attn.g_a_proj",
"model.layers.13.self_attn.g_b_proj",
"model.layers.13.self_attn.k_conv1d",
"model.layers.13.self_attn.k_proj",
"model.layers.13.self_attn.o_norm",
"model.layers.13.self_attn.o_proj",
"model.layers.13.self_attn.q_conv1d",
"model.layers.13.self_attn.q_proj",
"model.layers.13.self_attn.qkv_proj",
"model.layers.13.self_attn.v_conv1d",
"model.layers.13.self_attn.v_proj",
"model.layers.14.hc_attn_base",
"model.layers.14.hc_attn_fn",
"model.layers.14.hc_attn_scale",
"model.layers.14.hc_ffn_base",
"model.layers.14.hc_ffn_fn",
"model.layers.14.hc_ffn_scale",
"model.layers.14.input_layernorm",
"model.layers.14.mlp.gate",
"model.layers.14.mlp.gate.e_score_correction_bias",
"model.layers.14.post_attention_layernorm",
"model.layers.14.self_attn.A_log",
"model.layers.14.self_attn.b_proj",
"model.layers.14.self_attn.dt_bias",
"model.layers.14.self_attn.f_a_proj",
"model.layers.14.self_attn.f_b_proj",
"model.layers.14.self_attn.fused_qkvbfg_a_proj",
"model.layers.14.self_attn.g_a_proj",
"model.layers.14.self_attn.g_b_proj",
"model.layers.14.self_attn.k_conv1d",
"model.layers.14.self_attn.k_proj",
"model.layers.14.self_attn.o_norm",
"model.layers.14.self_attn.o_proj",
"model.layers.14.self_attn.q_conv1d",
"model.layers.14.self_attn.q_proj",
"model.layers.14.self_attn.qkv_proj",
"model.layers.14.self_attn.v_conv1d",
"model.layers.14.self_attn.v_proj",
"model.layers.15.hc_attn_base",
"model.layers.15.hc_attn_fn",
"model.layers.15.hc_attn_scale",
"model.layers.15.hc_ffn_base",
"model.layers.15.hc_ffn_fn",
"model.layers.15.hc_ffn_scale",
"model.layers.15.input_layernorm",
"model.layers.15.mlp.gate",
"model.layers.15.mlp.gate.e_score_correction_bias",
"model.layers.15.post_attention_layernorm",
"model.layers.15.self_attn.indexer.index_kpool_compress_ape",
"model.layers.15.self_attn.indexer.index_kpool_compress_gate",
"model.layers.15.self_attn.indexer.k_norm",
"model.layers.15.self_attn.indexer.k_norm.bias",
"model.layers.15.self_attn.indexer.weights_proj",
"model.layers.15.self_attn.indexer.wk",
"model.layers.15.self_attn.indexer.wq_b",
"model.layers.15.self_attn.kv_a_layernorm",
"model.layers.15.self_attn.kv_b_proj",
"model.layers.15.self_attn.q_a_layernorm",
"model.layers.16.hc_attn_base",
"model.layers.16.hc_attn_fn",
"model.layers.16.hc_attn_scale",
"model.layers.16.hc_ffn_base",
"model.layers.16.hc_ffn_fn",
"model.layers.16.hc_ffn_scale",
"model.layers.16.input_layernorm",
"model.layers.16.mlp.gate",
"model.layers.16.mlp.gate.e_score_correction_bias",
"model.layers.16.post_attention_layernorm",
"model.layers.16.self_attn.A_log",
"model.layers.16.self_attn.b_proj",
"model.layers.16.self_attn.dt_bias",
"model.layers.16.self_attn.f_a_proj",
"model.layers.16.self_attn.f_b_proj",
"model.layers.16.self_attn.fused_qkvbfg_a_proj",
"model.layers.16.self_attn.g_a_proj",
"model.layers.16.self_attn.g_b_proj",
"model.layers.16.self_attn.k_conv1d",
"model.layers.16.self_attn.k_proj",
"model.layers.16.self_attn.o_norm",
"model.layers.16.self_attn.o_proj",
"model.layers.16.self_attn.q_conv1d",
"model.layers.16.self_attn.q_proj",
"model.layers.16.self_attn.qkv_proj",
"model.layers.16.self_attn.v_conv1d",
"model.layers.16.self_attn.v_proj",
"model.layers.17.hc_attn_base",
"model.layers.17.hc_attn_fn",
"model.layers.17.hc_attn_scale",
"model.layers.17.hc_ffn_base",
"model.layers.17.hc_ffn_fn",
"model.layers.17.hc_ffn_scale",
"model.layers.17.input_layernorm",
"model.layers.17.mlp.gate",
"model.layers.17.mlp.gate.e_score_correction_bias",
"model.layers.17.post_attention_layernorm",
"model.layers.17.self_attn.A_log",
"model.layers.17.self_attn.b_proj",
"model.layers.17.self_attn.dt_bias",
"model.layers.17.self_attn.f_a_proj",
"model.layers.17.self_attn.f_b_proj",
"model.layers.17.self_attn.fused_qkvbfg_a_proj",
"model.layers.17.self_attn.g_a_proj",
"model.layers.17.self_attn.g_b_proj",
"model.layers.17.self_attn.k_conv1d",
"model.layers.17.self_attn.k_proj",
"model.layers.17.self_attn.o_norm",
"model.layers.17.self_attn.o_proj",
"model.layers.17.self_attn.q_conv1d",
"model.layers.17.self_attn.q_proj",
"model.layers.17.self_attn.qkv_proj",
"model.layers.17.self_attn.v_conv1d",
"model.layers.17.self_attn.v_proj",
"model.layers.18.hc_attn_base",
"model.layers.18.hc_attn_fn",
"model.layers.18.hc_attn_scale",
"model.layers.18.hc_ffn_base",
"model.layers.18.hc_ffn_fn",
"model.layers.18.hc_ffn_scale",
"model.layers.18.input_layernorm",
"model.layers.18.mlp.gate",
"model.layers.18.mlp.gate.e_score_correction_bias",
"model.layers.18.post_attention_layernorm",
"model.layers.18.self_attn.A_log",
"model.layers.18.self_attn.b_proj",
"model.layers.18.self_attn.dt_bias",
"model.layers.18.self_attn.f_a_proj",
"model.layers.18.self_attn.f_b_proj",
"model.layers.18.self_attn.fused_qkvbfg_a_proj",
"model.layers.18.self_attn.g_a_proj",
"model.layers.18.self_attn.g_b_proj",
"model.layers.18.self_attn.k_conv1d",
"model.layers.18.self_attn.k_proj",
"model.layers.18.self_attn.o_norm",
"model.layers.18.self_attn.o_proj",
"model.layers.18.self_attn.q_conv1d",
"model.layers.18.self_attn.q_proj",
"model.layers.18.self_attn.qkv_proj",
"model.layers.18.self_attn.v_conv1d",
"model.layers.18.self_attn.v_proj",
"model.layers.19.hc_attn_base",
"model.layers.19.hc_attn_fn",
"model.layers.19.hc_attn_scale",
"model.layers.19.hc_ffn_base",
"model.layers.19.hc_ffn_fn",
"model.layers.19.hc_ffn_scale",
"model.layers.19.input_layernorm",
"model.layers.19.mlp.gate",
"model.layers.19.mlp.gate.e_score_correction_bias",
"model.layers.19.post_attention_layernorm",
"model.layers.19.self_attn.indexer.index_kpool_compress_ape",
"model.layers.19.self_attn.indexer.index_kpool_compress_gate",
"model.layers.19.self_attn.indexer.k_norm",
"model.layers.19.self_attn.indexer.k_norm.bias",
"model.layers.19.self_attn.indexer.weights_proj",
"model.layers.19.self_attn.indexer.wk",
"model.layers.19.self_attn.indexer.wq_b",
"model.layers.19.self_attn.kv_a_layernorm",
"model.layers.19.self_attn.kv_b_proj",
"model.layers.19.self_attn.q_a_layernorm",
"model.layers.2.hc_attn_base",
"model.layers.2.hc_attn_fn",
"model.layers.2.hc_attn_scale",
"model.layers.2.hc_ffn_base",
"model.layers.2.hc_ffn_fn",
"model.layers.2.hc_ffn_scale",
"model.layers.2.input_layernorm",
"model.layers.2.post_attention_layernorm",
"model.layers.2.self_attn.A_log",
"model.layers.2.self_attn.b_proj",
"model.layers.2.self_attn.dt_bias",
"model.layers.2.self_attn.f_a_proj",
"model.layers.2.self_attn.f_b_proj",
"model.layers.2.self_attn.fused_qkvbfg_a_proj",
"model.layers.2.self_attn.g_a_proj",
"model.layers.2.self_attn.g_b_proj",
"model.layers.2.self_attn.k_conv1d",
"model.layers.2.self_attn.k_proj",
"model.layers.2.self_attn.o_norm",
"model.layers.2.self_attn.o_proj",
"model.layers.2.self_attn.q_conv1d",
"model.layers.2.self_attn.q_proj",
"model.layers.2.self_attn.qkv_proj",
"model.layers.2.self_attn.v_conv1d",
"model.layers.2.self_attn.v_proj",
"model.layers.20.hc_attn_base",
"model.layers.20.hc_attn_fn",
"model.layers.20.hc_attn_scale",
"model.layers.20.hc_ffn_base",
"model.layers.20.hc_ffn_fn",
"model.layers.20.hc_ffn_scale",
"model.layers.20.input_layernorm",
"model.layers.20.mlp.gate",
"model.layers.20.mlp.gate.e_score_correction_bias",
"model.layers.20.post_attention_layernorm",
"model.layers.20.self_attn.A_log",
"model.layers.20.self_attn.b_proj",
"model.layers.20.self_attn.dt_bias",
"model.layers.20.self_attn.f_a_proj",
"model.layers.20.self_attn.f_b_proj",
"model.layers.20.self_attn.fused_qkvbfg_a_proj",
"model.layers.20.self_attn.g_a_proj",
"model.layers.20.self_attn.g_b_proj",
"model.layers.20.self_attn.k_conv1d",
"model.layers.20.self_attn.k_proj",
"model.layers.20.self_attn.o_norm",
"model.layers.20.self_attn.o_proj",
"model.layers.20.self_attn.q_conv1d",
"model.layers.20.self_attn.q_proj",
"model.layers.20.self_attn.qkv_proj",
"model.layers.20.self_attn.v_conv1d",
"model.layers.20.self_attn.v_proj",
"model.layers.21.hc_attn_base",
"model.layers.21.hc_attn_fn",
"model.layers.21.hc_attn_scale",
"model.layers.21.hc_ffn_base",
"model.layers.21.hc_ffn_fn",
"model.layers.21.hc_ffn_scale",
"model.layers.21.input_layernorm",
"model.layers.21.mlp.gate",
"model.layers.21.mlp.gate.e_score_correction_bias",
"model.layers.21.post_attention_layernorm",
"model.layers.21.self_attn.A_log",
"model.layers.21.self_attn.b_proj",
"model.layers.21.self_attn.dt_bias",
"model.layers.21.self_attn.f_a_proj",
"model.layers.21.self_attn.f_b_proj",
"model.layers.21.self_attn.fused_qkvbfg_a_proj",
"model.layers.21.self_attn.g_a_proj",
"model.layers.21.self_attn.g_b_proj",
"model.layers.21.self_attn.k_conv1d",
"model.layers.21.self_attn.k_proj",
"model.layers.21.self_attn.o_norm",
"model.layers.21.self_attn.o_proj",
"model.layers.21.self_attn.q_conv1d",
"model.layers.21.self_attn.q_proj",
"model.layers.21.self_attn.qkv_proj",
"model.layers.21.self_attn.v_conv1d",
"model.layers.21.self_attn.v_proj",
"model.layers.22.hc_attn_base",
"model.layers.22.hc_attn_fn",
"model.layers.22.hc_attn_scale",
"model.layers.22.hc_ffn_base",
"model.layers.22.hc_ffn_fn",
"model.layers.22.hc_ffn_scale",
"model.layers.22.input_layernorm",
"model.layers.22.mlp.gate",
"model.layers.22.mlp.gate.e_score_correction_bias",
"model.layers.22.post_attention_layernorm",
"model.layers.22.self_attn.A_log",
"model.layers.22.self_attn.b_proj",
"model.layers.22.self_attn.dt_bias",
"model.layers.22.self_attn.f_a_proj",
"model.layers.22.self_attn.f_b_proj",
"model.layers.22.self_attn.fused_qkvbfg_a_proj",
"model.layers.22.self_attn.g_a_proj",
"model.layers.22.self_attn.g_b_proj",
"model.layers.22.self_attn.k_conv1d",
"model.layers.22.self_attn.k_proj",
"model.layers.22.self_attn.o_norm",
"model.layers.22.self_attn.o_proj",
"model.layers.22.self_attn.q_conv1d",
"model.layers.22.self_attn.q_proj",
"model.layers.22.self_attn.qkv_proj",
"model.layers.22.self_attn.v_conv1d",
"model.layers.22.self_attn.v_proj",
"model.layers.23.hc_attn_base",
"model.layers.23.hc_attn_fn",
"model.layers.23.hc_attn_scale",
"model.layers.23.hc_ffn_base",
"model.layers.23.hc_ffn_fn",
"model.layers.23.hc_ffn_scale",
"model.layers.23.input_layernorm",
"model.layers.23.mlp.gate",
"model.layers.23.mlp.gate.e_score_correction_bias",
"model.layers.23.post_attention_layernorm",
"model.layers.23.self_attn.indexer.index_kpool_compress_ape",
"model.layers.23.self_attn.indexer.index_kpool_compress_gate",
"model.layers.23.self_attn.indexer.k_norm",
"model.layers.23.self_attn.indexer.k_norm.bias",
"model.layers.23.self_attn.indexer.weights_proj",
"model.layers.23.self_attn.indexer.wk",
"model.layers.23.self_attn.indexer.wq_b",
"model.layers.23.self_attn.kv_a_layernorm",
"model.layers.23.self_attn.kv_b_proj",
"model.layers.23.self_attn.q_a_layernorm",
"model.layers.24.hc_attn_base",
"model.layers.24.hc_attn_fn",
"model.layers.24.hc_attn_scale",
"model.layers.24.hc_ffn_base",
"model.layers.24.hc_ffn_fn",
"model.layers.24.hc_ffn_scale",
"model.layers.24.input_layernorm",
"model.layers.24.mlp.gate",
"model.layers.24.mlp.gate.e_score_correction_bias",
"model.layers.24.post_attention_layernorm",
"model.layers.24.self_attn.A_log",
"model.layers.24.self_attn.b_proj",
"model.layers.24.self_attn.dt_bias",
"model.layers.24.self_attn.f_a_proj",
"model.layers.24.self_attn.f_b_proj",
"model.layers.24.self_attn.fused_qkvbfg_a_proj",
"model.layers.24.self_attn.g_a_proj",
"model.layers.24.self_attn.g_b_proj",
"model.layers.24.self_attn.k_conv1d",
"model.layers.24.self_attn.k_proj",
"model.layers.24.self_attn.o_norm",
"model.layers.24.self_attn.o_proj",
"model.layers.24.self_attn.q_conv1d",
"model.layers.24.self_attn.q_proj",
"model.layers.24.self_attn.qkv_proj",
"model.layers.24.self_attn.v_conv1d",
"model.layers.24.self_attn.v_proj",
"model.layers.25.hc_attn_base",
"model.layers.25.hc_attn_fn",
"model.layers.25.hc_attn_scale",
"model.layers.25.hc_ffn_base",
"model.layers.25.hc_ffn_fn",
"model.layers.25.hc_ffn_scale",
"model.layers.25.input_layernorm",
"model.layers.25.mlp.gate",
"model.layers.25.mlp.gate.e_score_correction_bias",
"model.layers.25.post_attention_layernorm",
"model.layers.25.self_attn.A_log",
"model.layers.25.self_attn.b_proj",
"model.layers.25.self_attn.dt_bias",
"model.layers.25.self_attn.f_a_proj",
"model.layers.25.self_attn.f_b_proj",
"model.layers.25.self_attn.fused_qkvbfg_a_proj",
"model.layers.25.self_attn.g_a_proj",
"model.layers.25.self_attn.g_b_proj",
"model.layers.25.self_attn.k_conv1d",
"model.layers.25.self_attn.k_proj",
"model.layers.25.self_attn.o_norm",
"model.layers.25.self_attn.o_proj",
"model.layers.25.self_attn.q_conv1d",
"model.layers.25.self_attn.q_proj",
"model.layers.25.self_attn.qkv_proj",
"model.layers.25.self_attn.v_conv1d",
"model.layers.25.self_attn.v_proj",
"model.layers.26.hc_attn_base",
"model.layers.26.hc_attn_fn",
"model.layers.26.hc_attn_scale",
"model.layers.26.hc_ffn_base",
"model.layers.26.hc_ffn_fn",
"model.layers.26.hc_ffn_scale",
"model.layers.26.input_layernorm",
"model.layers.26.mlp.gate",
"model.layers.26.mlp.gate.e_score_correction_bias",
"model.layers.26.post_attention_layernorm",
"model.layers.26.self_attn.A_log",
"model.layers.26.self_attn.b_proj",
"model.layers.26.self_attn.dt_bias",
"model.layers.26.self_attn.f_a_proj",
"model.layers.26.self_attn.f_b_proj",
"model.layers.26.self_attn.fused_qkvbfg_a_proj",
"model.layers.26.self_attn.g_a_proj",
"model.layers.26.self_attn.g_b_proj",
"model.layers.26.self_attn.k_conv1d",
"model.layers.26.self_attn.k_proj",
"model.layers.26.self_attn.o_norm",
"model.layers.26.self_attn.o_proj",
"model.layers.26.self_attn.q_conv1d",
"model.layers.26.self_attn.q_proj",
"model.layers.26.self_attn.qkv_proj",
"model.layers.26.self_attn.v_conv1d",
"model.layers.26.self_attn.v_proj",
"model.layers.27.hc_attn_base",
"model.layers.27.hc_attn_fn",
"model.layers.27.hc_attn_scale",
"model.layers.27.hc_ffn_base",
"model.layers.27.hc_ffn_fn",
"model.layers.27.hc_ffn_scale",
"model.layers.27.input_layernorm",
"model.layers.27.mlp.gate",
"model.layers.27.mlp.gate.e_score_correction_bias",
"model.layers.27.post_attention_layernorm",
"model.layers.27.self_attn.indexer.index_kpool_compress_ape",
"model.layers.27.self_attn.indexer.index_kpool_compress_gate",
"model.layers.27.self_attn.indexer.k_norm",
"model.layers.27.self_attn.indexer.k_norm.bias",
"model.layers.27.self_attn.indexer.weights_proj",
"model.layers.27.self_attn.indexer.wk",
"model.layers.27.self_attn.indexer.wq_b",
"model.layers.27.self_attn.kv_a_layernorm",
"model.layers.27.self_attn.kv_b_proj",
"model.layers.27.self_attn.q_a_layernorm",
"model.layers.28.hc_attn_base",
"model.layers.28.hc_attn_fn",
"model.layers.28.hc_attn_scale",
"model.layers.28.hc_ffn_base",
"model.layers.28.hc_ffn_fn",
"model.layers.28.hc_ffn_scale",
"model.layers.28.input_layernorm",
"model.layers.28.mlp.gate",
"model.layers.28.mlp.gate.e_score_correction_bias",
"model.layers.28.post_attention_layernorm",
"model.layers.28.self_attn.A_log",
"model.layers.28.self_attn.b_proj",
"model.layers.28.self_attn.dt_bias",
"model.layers.28.self_attn.f_a_proj",
"model.layers.28.self_attn.f_b_proj",
"model.layers.28.self_attn.fused_qkvbfg_a_proj",
"model.layers.28.self_attn.g_a_proj",
"model.layers.28.self_attn.g_b_proj",
"model.layers.28.self_attn.k_conv1d",
"model.layers.28.self_attn.k_proj",
"model.layers.28.self_attn.o_norm",
"model.layers.28.self_attn.o_proj",
"model.layers.28.self_attn.q_conv1d",
"model.layers.28.self_attn.q_proj",
"model.layers.28.self_attn.qkv_proj",
"model.layers.28.self_attn.v_conv1d",
"model.layers.28.self_attn.v_proj",
"model.layers.29.hc_attn_base",
"model.layers.29.hc_attn_fn",
"model.layers.29.hc_attn_scale",
"model.layers.29.hc_ffn_base",
"model.layers.29.hc_ffn_fn",
"model.layers.29.hc_ffn_scale",
"model.layers.29.input_layernorm",
"model.layers.29.mlp.gate",
"model.layers.29.mlp.gate.e_score_correction_bias",
"model.layers.29.post_attention_layernorm",
"model.layers.29.self_attn.A_log",
"model.layers.29.self_attn.b_proj",
"model.layers.29.self_attn.dt_bias",
"model.layers.29.self_attn.f_a_proj",
"model.layers.29.self_attn.f_b_proj",
"model.layers.29.self_attn.fused_qkvbfg_a_proj",
"model.layers.29.self_attn.g_a_proj",
"model.layers.29.self_attn.g_b_proj",
"model.layers.29.self_attn.k_conv1d",
"model.layers.29.self_attn.k_proj",
"model.layers.29.self_attn.o_norm",
"model.layers.29.self_attn.o_proj",
"model.layers.29.self_attn.q_conv1d",
"model.layers.29.self_attn.q_proj",
"model.layers.29.self_attn.qkv_proj",
"model.layers.29.self_attn.v_conv1d",
"model.layers.29.self_attn.v_proj",
"model.layers.3.hc_attn_base",
"model.layers.3.hc_attn_fn",
"model.layers.3.hc_attn_scale",
"model.layers.3.hc_ffn_base",
"model.layers.3.hc_ffn_fn",
"model.layers.3.hc_ffn_scale",
"model.layers.3.input_layernorm",
"model.layers.3.mlp.gate",
"model.layers.3.mlp.gate.e_score_correction_bias",
"model.layers.3.post_attention_layernorm",
"model.layers.3.self_attn.indexer.index_kpool_compress_ape",
"model.layers.3.self_attn.indexer.index_kpool_compress_gate",
"model.layers.3.self_attn.indexer.k_norm",
"model.layers.3.self_attn.indexer.k_norm.bias",
"model.layers.3.self_attn.indexer.weights_proj",
"model.layers.3.self_attn.indexer.wk",
"model.layers.3.self_attn.indexer.wq_b",
"model.layers.3.self_attn.kv_a_layernorm",
"model.layers.3.self_attn.kv_b_proj",
"model.layers.3.self_attn.q_a_layernorm",
"model.layers.30.hc_attn_base",
"model.layers.30.hc_attn_fn",
"model.layers.30.hc_attn_scale",
"model.layers.30.hc_ffn_base",
"model.layers.30.hc_ffn_fn",
"model.layers.30.hc_ffn_scale",
"model.layers.30.input_layernorm",
"model.layers.30.mlp.gate",
"model.layers.30.mlp.gate.e_score_correction_bias",
"model.layers.30.post_attention_layernorm",
"model.layers.30.self_attn.A_log",
"model.layers.30.self_attn.b_proj",
"model.layers.30.self_attn.dt_bias",
"model.layers.30.self_attn.f_a_proj",
"model.layers.30.self_attn.f_b_proj",
"model.layers.30.self_attn.fused_qkvbfg_a_proj",
"model.layers.30.self_attn.g_a_proj",
"model.layers.30.self_attn.g_b_proj",
"model.layers.30.self_attn.k_conv1d",
"model.layers.30.self_attn.k_proj",
"model.layers.30.self_attn.o_norm",
"model.layers.30.self_attn.o_proj",
"model.layers.30.self_attn.q_conv1d",
"model.layers.30.self_attn.q_proj",
"model.layers.30.self_attn.qkv_proj",
"model.layers.30.self_attn.v_conv1d",
"model.layers.30.self_attn.v_proj",
"model.layers.31.hc_attn_base",
"model.layers.31.hc_attn_fn",
"model.layers.31.hc_attn_scale",
"model.layers.31.hc_ffn_base",
"model.layers.31.hc_ffn_fn",
"model.layers.31.hc_ffn_scale",
"model.layers.31.input_layernorm",
"model.layers.31.mlp.gate",
"model.layers.31.mlp.gate.e_score_correction_bias",
"model.layers.31.post_attention_layernorm",
"model.layers.31.self_attn.indexer.index_kpool_compress_ape",
"model.layers.31.self_attn.indexer.index_kpool_compress_gate",
"model.layers.31.self_attn.indexer.k_norm",
"model.layers.31.self_attn.indexer.k_norm.bias",
"model.layers.31.self_attn.indexer.weights_proj",
"model.layers.31.self_attn.indexer.wk",
"model.layers.31.self_attn.indexer.wq_b",
"model.layers.31.self_attn.kv_a_layernorm",
"model.layers.31.self_attn.kv_b_proj",
"model.layers.31.self_attn.q_a_layernorm",
"model.layers.32.hc_attn_base",
"model.layers.32.hc_attn_fn",
"model.layers.32.hc_attn_scale",
"model.layers.32.hc_ffn_base",
"model.layers.32.hc_ffn_fn",
"model.layers.32.hc_ffn_scale",
"model.layers.32.input_layernorm",
"model.layers.32.mlp.gate",
"model.layers.32.mlp.gate.e_score_correction_bias",
"model.layers.32.post_attention_layernorm",
"model.layers.32.self_attn.A_log",
"model.layers.32.self_attn.b_proj",
"model.layers.32.self_attn.dt_bias",
"model.layers.32.self_attn.f_a_proj",
"model.layers.32.self_attn.f_b_proj",
"model.layers.32.self_attn.fused_qkvbfg_a_proj",
"model.layers.32.self_attn.g_a_proj",
"model.layers.32.self_attn.g_b_proj",
"model.layers.32.self_attn.k_conv1d",
"model.layers.32.self_attn.k_proj",
"model.layers.32.self_attn.o_norm",
"model.layers.32.self_attn.o_proj",
"model.layers.32.self_attn.q_conv1d",
"model.layers.32.self_attn.q_proj",
"model.layers.32.self_attn.qkv_proj",
"model.layers.32.self_attn.v_conv1d",
"model.layers.32.self_attn.v_proj",
"model.layers.33.hc_attn_base",
"model.layers.33.hc_attn_fn",
"model.layers.33.hc_attn_scale",
"model.layers.33.hc_ffn_base",
"model.layers.33.hc_ffn_fn",
"model.layers.33.hc_ffn_scale",
"model.layers.33.input_layernorm",
"model.layers.33.mlp.gate",
"model.layers.33.mlp.gate.e_score_correction_bias",
"model.layers.33.post_attention_layernorm",
"model.layers.33.self_attn.A_log",
"model.layers.33.self_attn.b_proj",
"model.layers.33.self_attn.dt_bias",
"model.layers.33.self_attn.f_a_proj",
"model.layers.33.self_attn.f_b_proj",
"model.layers.33.self_attn.fused_qkvbfg_a_proj",
"model.layers.33.self_attn.g_a_proj",
"model.layers.33.self_attn.g_b_proj",
"model.layers.33.self_attn.k_conv1d",
"model.layers.33.self_attn.k_proj",
"model.layers.33.self_attn.o_norm",
"model.layers.33.self_attn.o_proj",
"model.layers.33.self_attn.q_conv1d",
"model.layers.33.self_attn.q_proj",
"model.layers.33.self_attn.qkv_proj",
"model.layers.33.self_attn.v_conv1d",
"model.layers.33.self_attn.v_proj",
"model.layers.34.hc_attn_base",
"model.layers.34.hc_attn_fn",
"model.layers.34.hc_attn_scale",
"model.layers.34.hc_ffn_base",
"model.layers.34.hc_ffn_fn",
"model.layers.34.hc_ffn_scale",
"model.layers.34.input_layernorm",
"model.layers.34.mlp.gate",
"model.layers.34.mlp.gate.e_score_correction_bias",
"model.layers.34.post_attention_layernorm",
"model.layers.34.self_attn.A_log",
"model.layers.34.self_attn.b_proj",
"model.layers.34.self_attn.dt_bias",
"model.layers.34.self_attn.f_a_proj",
"model.layers.34.self_attn.f_b_proj",
"model.layers.34.self_attn.fused_qkvbfg_a_proj",
"model.layers.34.self_attn.g_a_proj",
"model.layers.34.self_attn.g_b_proj",
"model.layers.34.self_attn.k_conv1d",
"model.layers.34.self_attn.k_proj",
"model.layers.34.self_attn.o_norm",
"model.layers.34.self_attn.o_proj",
"model.layers.34.self_attn.q_conv1d",
"model.layers.34.self_attn.q_proj",
"model.layers.34.self_attn.qkv_proj",
"model.layers.34.self_attn.v_conv1d",
"model.layers.34.self_attn.v_proj",
"model.layers.35.hc_attn_base",
"model.layers.35.hc_attn_fn",
"model.layers.35.hc_attn_scale",
"model.layers.35.hc_ffn_base",
"model.layers.35.hc_ffn_fn",
"model.layers.35.hc_ffn_scale",
"model.layers.35.input_layernorm",
"model.layers.35.mlp.gate",
"model.layers.35.mlp.gate.e_score_correction_bias",
"model.layers.35.post_attention_layernorm",
"model.layers.35.self_attn.indexer.index_kpool_compress_ape",
"model.layers.35.self_attn.indexer.index_kpool_compress_gate",
"model.layers.35.self_attn.indexer.k_norm",
"model.layers.35.self_attn.indexer.k_norm.bias",
"model.layers.35.self_attn.indexer.weights_proj",
"model.layers.35.self_attn.indexer.wk",
"model.layers.35.self_attn.indexer.wq_b",
"model.layers.35.self_attn.kv_a_layernorm",
"model.layers.35.self_attn.kv_b_proj",
"model.layers.35.self_attn.q_a_layernorm",
"model.layers.36.hc_attn_base",
"model.layers.36.hc_attn_fn",
"model.layers.36.hc_attn_scale",
"model.layers.36.hc_ffn_base",
"model.layers.36.hc_ffn_fn",
"model.layers.36.hc_ffn_scale",
"model.layers.36.input_layernorm",
"model.layers.36.mlp.gate",
"model.layers.36.mlp.gate.e_score_correction_bias",
"model.layers.36.post_attention_layernorm",
"model.layers.36.self_attn.A_log",
"model.layers.36.self_attn.b_proj",
"model.layers.36.self_attn.dt_bias",
"model.layers.36.self_attn.f_a_proj",
"model.layers.36.self_attn.f_b_proj",
"model.layers.36.self_attn.fused_qkvbfg_a_proj",
"model.layers.36.self_attn.g_a_proj",
"model.layers.36.self_attn.g_b_proj",
"model.layers.36.self_attn.k_conv1d",
"model.layers.36.self_attn.k_proj",
"model.layers.36.self_attn.o_norm",
"model.layers.36.self_attn.o_proj",
"model.layers.36.self_attn.q_conv1d",
"model.layers.36.self_attn.q_proj",
"model.layers.36.self_attn.qkv_proj",
"model.layers.36.self_attn.v_conv1d",
"model.layers.36.self_attn.v_proj",
"model.layers.37.hc_attn_base",
"model.layers.37.hc_attn_fn",
"model.layers.37.hc_attn_scale",
"model.layers.37.hc_ffn_base",
"model.layers.37.hc_ffn_fn",
"model.layers.37.hc_ffn_scale",
"model.layers.37.input_layernorm",
"model.layers.37.mlp.gate",
"model.layers.37.mlp.gate.e_score_correction_bias",
"model.layers.37.post_attention_layernorm",
"model.layers.37.self_attn.A_log",
"model.layers.37.self_attn.b_proj",
"model.layers.37.self_attn.dt_bias",
"model.layers.37.self_attn.f_a_proj",
"model.layers.37.self_attn.f_b_proj",
"model.layers.37.self_attn.fused_qkvbfg_a_proj",
"model.layers.37.self_attn.g_a_proj",
"model.layers.37.self_attn.g_b_proj",
"model.layers.37.self_attn.k_conv1d",
"model.layers.37.self_attn.k_proj",
"model.layers.37.self_attn.o_norm",
"model.layers.37.self_attn.o_proj",
"model.layers.37.self_attn.q_conv1d",
"model.layers.37.self_attn.q_proj",
"model.layers.37.self_attn.qkv_proj",
"model.layers.37.self_attn.v_conv1d",
"model.layers.37.self_attn.v_proj",
"model.layers.38.hc_attn_base",
"model.layers.38.hc_attn_fn",
"model.layers.38.hc_attn_scale",
"model.layers.38.hc_ffn_base",
"model.layers.38.hc_ffn_fn",
"model.layers.38.hc_ffn_scale",
"model.layers.38.input_layernorm",
"model.layers.38.mlp.gate",
"model.layers.38.mlp.gate.e_score_correction_bias",
"model.layers.38.post_attention_layernorm",
"model.layers.38.self_attn.A_log",
"model.layers.38.self_attn.b_proj",
"model.layers.38.self_attn.dt_bias",
"model.layers.38.self_attn.f_a_proj",
"model.layers.38.self_attn.f_b_proj",
"model.layers.38.self_attn.fused_qkvbfg_a_proj",
"model.layers.38.self_attn.g_a_proj",
"model.layers.38.self_attn.g_b_proj",
"model.layers.38.self_attn.k_conv1d",
"model.layers.38.self_attn.k_proj",
"model.layers.38.self_attn.o_norm",
"model.layers.38.self_attn.o_proj",
"model.layers.38.self_attn.q_conv1d",
"model.layers.38.self_attn.q_proj",
"model.layers.38.self_attn.qkv_proj",
"model.layers.38.self_attn.v_conv1d",
"model.layers.38.self_attn.v_proj",
"model.layers.39.hc_attn_base",
"model.layers.39.hc_attn_fn",
"model.layers.39.hc_attn_scale",
"model.layers.39.hc_ffn_base",
"model.layers.39.hc_ffn_fn",
"model.layers.39.hc_ffn_scale",
"model.layers.39.input_layernorm",
"model.layers.39.mlp.gate",
"model.layers.39.mlp.gate.e_score_correction_bias",
"model.layers.39.post_attention_layernorm",
"model.layers.39.self_attn.indexer.index_kpool_compress_ape",
"model.layers.39.self_attn.indexer.index_kpool_compress_gate",
"model.layers.39.self_attn.indexer.k_norm",
"model.layers.39.self_attn.indexer.k_norm.bias",
"model.layers.39.self_attn.indexer.weights_proj",
"model.layers.39.self_attn.indexer.wk",
"model.layers.39.self_attn.indexer.wq_b",
"model.layers.39.self_attn.kv_a_layernorm",
"model.layers.39.self_attn.kv_b_proj",
"model.layers.39.self_attn.q_a_layernorm",
"model.layers.4.hc_attn_base",
"model.layers.4.hc_attn_fn",
"model.layers.4.hc_attn_scale",
"model.layers.4.hc_ffn_base",
"model.layers.4.hc_ffn_fn",
"model.layers.4.hc_ffn_scale",
"model.layers.4.input_layernorm",
"model.layers.4.mlp.gate",
"model.layers.4.mlp.gate.e_score_correction_bias",
"model.layers.4.post_attention_layernorm",
"model.layers.4.self_attn.A_log",
"model.layers.4.self_attn.b_proj",
"model.layers.4.self_attn.dt_bias",
"model.layers.4.self_attn.f_a_proj",
"model.layers.4.self_attn.f_b_proj",
"model.layers.4.self_attn.fused_qkvbfg_a_proj",
"model.layers.4.self_attn.g_a_proj",
"model.layers.4.self_attn.g_b_proj",
"model.layers.4.self_attn.k_conv1d",
"model.layers.4.self_attn.k_proj",
"model.layers.4.self_attn.o_norm",
"model.layers.4.self_attn.o_proj",
"model.layers.4.self_attn.q_conv1d",
"model.layers.4.self_attn.q_proj",
"model.layers.4.self_attn.qkv_proj",
"model.layers.4.self_attn.v_conv1d",
"model.layers.4.self_attn.v_proj",
"model.layers.40.hc_attn_base",
"model.layers.40.hc_attn_fn",
"model.layers.40.hc_attn_scale",
"model.layers.40.hc_ffn_base",
"model.layers.40.hc_ffn_fn",
"model.layers.40.hc_ffn_scale",
"model.layers.40.input_layernorm",
"model.layers.40.mlp.gate",
"model.layers.40.mlp.gate.e_score_correction_bias",
"model.layers.40.post_attention_layernorm",
"model.layers.40.self_attn.A_log",
"model.layers.40.self_attn.b_proj",
"model.layers.40.self_attn.dt_bias",
"model.layers.40.self_attn.f_a_proj",
"model.layers.40.self_attn.f_b_proj",
"model.layers.40.self_attn.fused_qkvbfg_a_proj",
"model.layers.40.self_attn.g_a_proj",
"model.layers.40.self_attn.g_b_proj",
"model.layers.40.self_attn.k_conv1d",
"model.layers.40.self_attn.k_proj",
"model.layers.40.self_attn.o_norm",
"model.layers.40.self_attn.o_proj",
"model.layers.40.self_attn.q_conv1d",
"model.layers.40.self_attn.q_proj",
"model.layers.40.self_attn.qkv_proj",
"model.layers.40.self_attn.v_conv1d",
"model.layers.40.self_attn.v_proj",
"model.layers.41.hc_attn_base",
"model.layers.41.hc_attn_fn",
"model.layers.41.hc_attn_scale",
"model.layers.41.hc_ffn_base",
"model.layers.41.hc_ffn_fn",
"model.layers.41.hc_ffn_scale",
"model.layers.41.input_layernorm",
"model.layers.41.mlp.gate",
"model.layers.41.mlp.gate.e_score_correction_bias",
"model.layers.41.post_attention_layernorm",
"model.layers.41.self_attn.A_log",
"model.layers.41.self_attn.b_proj",
"model.layers.41.self_attn.dt_bias",
"model.layers.41.self_attn.f_a_proj",
"model.layers.41.self_attn.f_b_proj",
"model.layers.41.self_attn.fused_qkvbfg_a_proj",
"model.layers.41.self_attn.g_a_proj",
"model.layers.41.self_attn.g_b_proj",
"model.layers.41.self_attn.k_conv1d",
"model.layers.41.self_attn.k_proj",
"model.layers.41.self_attn.o_norm",
"model.layers.41.self_attn.o_proj",
"model.layers.41.self_attn.q_conv1d",
"model.layers.41.self_attn.q_proj",
"model.layers.41.self_attn.qkv_proj",
"model.layers.41.self_attn.v_conv1d",
"model.layers.41.self_attn.v_proj",
"model.layers.42.hc_attn_base",
"model.layers.42.hc_attn_fn",
"model.layers.42.hc_attn_scale",
"model.layers.42.hc_ffn_base",
"model.layers.42.hc_ffn_fn",
"model.layers.42.hc_ffn_scale",
"model.layers.42.input_layernorm",
"model.layers.42.mlp.gate",
"model.layers.42.mlp.gate.e_score_correction_bias",
"model.layers.42.post_attention_layernorm",
"model.layers.42.self_attn.A_log",
"model.layers.42.self_attn.b_proj",
"model.layers.42.self_attn.dt_bias",
"model.layers.42.self_attn.f_a_proj",
"model.layers.42.self_attn.f_b_proj",
"model.layers.42.self_attn.fused_qkvbfg_a_proj",
"model.layers.42.self_attn.g_a_proj",
"model.layers.42.self_attn.g_b_proj",
"model.layers.42.self_attn.k_conv1d",
"model.layers.42.self_attn.k_proj",
"model.layers.42.self_attn.o_norm",
"model.layers.42.self_attn.o_proj",
"model.layers.42.self_attn.q_conv1d",
"model.layers.42.self_attn.q_proj",
"model.layers.42.self_attn.qkv_proj",
"model.layers.42.self_attn.v_conv1d",
"model.layers.42.self_attn.v_proj",
"model.layers.43.hc_attn_base",
"model.layers.43.hc_attn_fn",
"model.layers.43.hc_attn_scale",
"model.layers.43.hc_ffn_base",
"model.layers.43.hc_ffn_fn",
"model.layers.43.hc_ffn_scale",
"model.layers.43.input_layernorm",
"model.layers.43.mlp.gate",
"model.layers.43.mlp.gate.e_score_correction_bias",
"model.layers.43.post_attention_layernorm",
"model.layers.43.self_attn.indexer.index_kpool_compress_ape",
"model.layers.43.self_attn.indexer.index_kpool_compress_gate",
"model.layers.43.self_attn.indexer.k_norm",
"model.layers.43.self_attn.indexer.k_norm.bias",
"model.layers.43.self_attn.indexer.weights_proj",
"model.layers.43.self_attn.indexer.wk",
"model.layers.43.self_attn.indexer.wq_b",
"model.layers.43.self_attn.kv_a_layernorm",
"model.layers.43.self_attn.kv_b_proj",
"model.layers.43.self_attn.q_a_layernorm",
"model.layers.44.hc_attn_base",
"model.layers.44.hc_attn_fn",
"model.layers.44.hc_attn_scale",
"model.layers.44.hc_ffn_base",
"model.layers.44.hc_ffn_fn",
"model.layers.44.hc_ffn_scale",
"model.layers.44.input_layernorm",
"model.layers.44.mlp.gate",
"model.layers.44.mlp.gate.e_score_correction_bias",
"model.layers.44.post_attention_layernorm",
"model.layers.44.self_attn.A_log",
"model.layers.44.self_attn.b_proj",
"model.layers.44.self_attn.dt_bias",
"model.layers.44.self_attn.f_a_proj",
"model.layers.44.self_attn.f_b_proj",
"model.layers.44.self_attn.fused_qkvbfg_a_proj",
"model.layers.44.self_attn.g_a_proj",
"model.layers.44.self_attn.g_b_proj",
"model.layers.44.self_attn.k_conv1d",
"model.layers.44.self_attn.k_proj",
"model.layers.44.self_attn.o_norm",
"model.layers.44.self_attn.o_proj",
"model.layers.44.self_attn.q_conv1d",
"model.layers.44.self_attn.q_proj",
"model.layers.44.self_attn.qkv_proj",
"model.layers.44.self_attn.v_conv1d",
"model.layers.44.self_attn.v_proj",
"model.layers.45.eh_proj",
"model.layers.45.enorm",
"model.layers.45.hnorm",
"model.layers.45.input_layernorm",
"model.layers.45.mlp.gate",
"model.layers.45.mlp.gate.e_score_correction_bias",
"model.layers.45.post_attention_layernorm",
"model.layers.45.self_attn.indexer.index_kpool_compress_ape",
"model.layers.45.self_attn.indexer.index_kpool_compress_gate",
"model.layers.45.self_attn.indexer.k_norm",
"model.layers.45.self_attn.indexer.k_norm.bias",
"model.layers.45.self_attn.indexer.weights_proj",
"model.layers.45.self_attn.indexer.wk",
"model.layers.45.self_attn.indexer.wq_b",
"model.layers.45.self_attn.kv_a_layernorm",
"model.layers.45.self_attn.kv_b_proj",
"model.layers.45.self_attn.q_a_layernorm",
"model.layers.45.shared_head.norm",
"model.layers.5.hc_attn_base",
"model.layers.5.hc_attn_fn",
"model.layers.5.hc_attn_scale",
"model.layers.5.hc_ffn_base",
"model.layers.5.hc_ffn_fn",
"model.layers.5.hc_ffn_scale",
"model.layers.5.input_layernorm",
"model.layers.5.mlp.gate",
"model.layers.5.mlp.gate.e_score_correction_bias",
"model.layers.5.post_attention_layernorm",
"model.layers.5.self_attn.A_log",
"model.layers.5.self_attn.b_proj",
"model.layers.5.self_attn.dt_bias",
"model.layers.5.self_attn.f_a_proj",
"model.layers.5.self_attn.f_b_proj",
"model.layers.5.self_attn.fused_qkvbfg_a_proj",
"model.layers.5.self_attn.g_a_proj",
"model.layers.5.self_attn.g_b_proj",
"model.layers.5.self_attn.k_conv1d",
"model.layers.5.self_attn.k_proj",
"model.layers.5.self_attn.o_norm",
"model.layers.5.self_attn.o_proj",
"model.layers.5.self_attn.q_conv1d",
"model.layers.5.self_attn.q_proj",
"model.layers.5.self_attn.qkv_proj",
"model.layers.5.self_attn.v_conv1d",
"model.layers.5.self_attn.v_proj",
"model.layers.6.hc_attn_base",
"model.layers.6.hc_attn_fn",
"model.layers.6.hc_attn_scale",
"model.layers.6.hc_ffn_base",
"model.layers.6.hc_ffn_fn",
"model.layers.6.hc_ffn_scale",
"model.layers.6.input_layernorm",
"model.layers.6.mlp.gate",
"model.layers.6.mlp.gate.e_score_correction_bias",
"model.layers.6.post_attention_layernorm",
"model.layers.6.self_attn.A_log",
"model.layers.6.self_attn.b_proj",
"model.layers.6.self_attn.dt_bias",
"model.layers.6.self_attn.f_a_proj",
"model.layers.6.self_attn.f_b_proj",
"model.layers.6.self_attn.fused_qkvbfg_a_proj",
"model.layers.6.self_attn.g_a_proj",
"model.layers.6.self_attn.g_b_proj",
"model.layers.6.self_attn.k_conv1d",
"model.layers.6.self_attn.k_proj",
"model.layers.6.self_attn.o_norm",
"model.layers.6.self_attn.o_proj",
"model.layers.6.self_attn.q_conv1d",
"model.layers.6.self_attn.q_proj",
"model.layers.6.self_attn.qkv_proj",
"model.layers.6.self_attn.v_conv1d",
"model.layers.6.self_attn.v_proj",
"model.layers.7.hc_attn_base",
"model.layers.7.hc_attn_fn",
"model.layers.7.hc_attn_scale",
"model.layers.7.hc_ffn_base",
"model.layers.7.hc_ffn_fn",
"model.layers.7.hc_ffn_scale",
"model.layers.7.input_layernorm",
"model.layers.7.mlp.gate",
"model.layers.7.mlp.gate.e_score_correction_bias",
"model.layers.7.post_attention_layernorm",
"model.layers.7.self_attn.indexer.index_kpool_compress_ape",
"model.layers.7.self_attn.indexer.index_kpool_compress_gate",
"model.layers.7.self_attn.indexer.k_norm",
"model.layers.7.self_attn.indexer.k_norm.bias",
"model.layers.7.self_attn.indexer.weights_proj",
"model.layers.7.self_attn.indexer.wk",
"model.layers.7.self_attn.indexer.wq_b",
"model.layers.7.self_attn.kv_a_layernorm",
"model.layers.7.self_attn.kv_b_proj",
"model.layers.7.self_attn.q_a_layernorm",
"model.layers.8.hc_attn_base",
"model.layers.8.hc_attn_fn",
"model.layers.8.hc_attn_scale",
"model.layers.8.hc_ffn_base",
"model.layers.8.hc_ffn_fn",
"model.layers.8.hc_ffn_scale",
"model.layers.8.input_layernorm",
"model.layers.8.mlp.gate",
"model.layers.8.mlp.gate.e_score_correction_bias",
"model.layers.8.post_attention_layernorm",
"model.layers.8.self_attn.A_log",
"model.layers.8.self_attn.b_proj",
"model.layers.8.self_attn.dt_bias",
"model.layers.8.self_attn.f_a_proj",
"model.layers.8.self_attn.f_b_proj",
"model.layers.8.self_attn.fused_qkvbfg_a_proj",
"model.layers.8.self_attn.g_a_proj",
"model.layers.8.self_attn.g_b_proj",
"model.layers.8.self_attn.k_conv1d",
"model.layers.8.self_attn.k_proj",
"model.layers.8.self_attn.o_norm",
"model.layers.8.self_attn.o_proj",
"model.layers.8.self_attn.q_conv1d",
"model.layers.8.self_attn.q_proj",
"model.layers.8.self_attn.qkv_proj",
"model.layers.8.self_attn.v_conv1d",
"model.layers.8.self_attn.v_proj",
"model.layers.9.hc_attn_base",
"model.layers.9.hc_attn_fn",
"model.layers.9.hc_attn_scale",
"model.layers.9.hc_ffn_base",
"model.layers.9.hc_ffn_fn",
"model.layers.9.hc_ffn_scale",
"model.layers.9.input_layernorm",
"model.layers.9.mlp.gate",
"model.layers.9.mlp.gate.e_score_correction_bias",
"model.layers.9.post_attention_layernorm",
"model.layers.9.self_attn.A_log",
"model.layers.9.self_attn.b_proj",
"model.layers.9.self_attn.dt_bias",
"model.layers.9.self_attn.f_a_proj",
"model.layers.9.self_attn.f_b_proj",
"model.layers.9.self_attn.fused_qkvbfg_a_proj",
"model.layers.9.self_attn.g_a_proj",
"model.layers.9.self_attn.g_b_proj",
"model.layers.9.self_attn.k_conv1d",
"model.layers.9.self_attn.k_proj",
"model.layers.9.self_attn.o_norm",
"model.layers.9.self_attn.o_proj",
"model.layers.9.self_attn.q_conv1d",
"model.layers.9.self_attn.q_proj",
"model.layers.9.self_attn.qkv_proj",
"model.layers.9.self_attn.v_conv1d",
"model.layers.9.self_attn.v_proj",
"model.norm",
"model.visual",
"router",
"visual",
"visual.blocks.0.attn.k_norm",
"visual.blocks.0.attn.proj",
"visual.blocks.0.attn.proj.bias",
"visual.blocks.0.attn.q_norm",
"visual.blocks.0.attn.qkv",
"visual.blocks.0.attn.qkv.bias",
"visual.blocks.0.mlp.down_proj",
"visual.blocks.0.mlp.down_proj.bias",
"visual.blocks.0.mlp.gate_proj",
"visual.blocks.0.mlp.gate_proj.bias",
"visual.blocks.0.mlp.up_proj",
"visual.blocks.0.mlp.up_proj.bias",
"visual.blocks.0.norm1",
"visual.blocks.0.norm2",
"visual.blocks.1.attn.k_norm",
"visual.blocks.1.attn.proj",
"visual.blocks.1.attn.proj.bias",
"visual.blocks.1.attn.q_norm",
"visual.blocks.1.attn.qkv",
"visual.blocks.1.attn.qkv.bias",
"visual.blocks.1.mlp.down_proj",
"visual.blocks.1.mlp.down_proj.bias",
"visual.blocks.1.mlp.gate_proj",
"visual.blocks.1.mlp.gate_proj.bias",
"visual.blocks.1.mlp.up_proj",
"visual.blocks.1.mlp.up_proj.bias",
"visual.blocks.1.norm1",
"visual.blocks.1.norm2",
"visual.blocks.10.attn.k_norm",
"visual.blocks.10.attn.proj",
"visual.blocks.10.attn.proj.bias",
"visual.blocks.10.attn.q_norm",
"visual.blocks.10.attn.qkv",
"visual.blocks.10.attn.qkv.bias",
"visual.blocks.10.mlp.down_proj",
"visual.blocks.10.mlp.down_proj.bias",
"visual.blocks.10.mlp.gate_proj",
"visual.blocks.10.mlp.gate_proj.bias",
"visual.blocks.10.mlp.up_proj",
"visual.blocks.10.mlp.up_proj.bias",
"visual.blocks.10.norm1",
"visual.blocks.10.norm2",
"visual.blocks.11.attn.k_norm",
"visual.blocks.11.attn.proj",
"visual.blocks.11.attn.proj.bias",
"visual.blocks.11.attn.q_norm",
"visual.blocks.11.attn.qkv",
"visual.blocks.11.attn.qkv.bias",
"visual.blocks.11.mlp.down_proj",
"visual.blocks.11.mlp.down_proj.bias",
"visual.blocks.11.mlp.gate_proj",
"visual.blocks.11.mlp.gate_proj.bias",
"visual.blocks.11.mlp.up_proj",
"visual.blocks.11.mlp.up_proj.bias",
"visual.blocks.11.norm1",
"visual.blocks.11.norm2",
"visual.blocks.12.attn.k_norm",
"visual.blocks.12.attn.proj",
"visual.blocks.12.attn.proj.bias",
"visual.blocks.12.attn.q_norm",
"visual.blocks.12.attn.qkv",
"visual.blocks.12.attn.qkv.bias",
"visual.blocks.12.mlp.down_proj",
"visual.blocks.12.mlp.down_proj.bias",
"visual.blocks.12.mlp.gate_proj",
"visual.blocks.12.mlp.gate_proj.bias",
"visual.blocks.12.mlp.up_proj",
"visual.blocks.12.mlp.up_proj.bias",
"visual.blocks.12.norm1",
"visual.blocks.12.norm2",
"visual.blocks.13.attn.k_norm",
"visual.blocks.13.attn.proj",
"visual.blocks.13.attn.proj.bias",
"visual.blocks.13.attn.q_norm",
"visual.blocks.13.attn.qkv",
"visual.blocks.13.attn.qkv.bias",
"visual.blocks.13.mlp.down_proj",
"visual.blocks.13.mlp.down_proj.bias",
"visual.blocks.13.mlp.gate_proj",
"visual.blocks.13.mlp.gate_proj.bias",
"visual.blocks.13.mlp.up_proj",
"visual.blocks.13.mlp.up_proj.bias",
"visual.blocks.13.norm1",
"visual.blocks.13.norm2",
"visual.blocks.14.attn.k_norm",
"visual.blocks.14.attn.proj",
"visual.blocks.14.attn.proj.bias",
"visual.blocks.14.attn.q_norm",
"visual.blocks.14.attn.qkv",
"visual.blocks.14.attn.qkv.bias",
"visual.blocks.14.mlp.down_proj",
"visual.blocks.14.mlp.down_proj.bias",
"visual.blocks.14.mlp.gate_proj",
"visual.blocks.14.mlp.gate_proj.bias",
"visual.blocks.14.mlp.up_proj",
"visual.blocks.14.mlp.up_proj.bias",
"visual.blocks.14.norm1",
"visual.blocks.14.norm2",
"visual.blocks.15.attn.k_norm",
"visual.blocks.15.attn.proj",
"visual.blocks.15.attn.proj.bias",
"visual.blocks.15.attn.q_norm",
"visual.blocks.15.attn.qkv",
"visual.blocks.15.attn.qkv.bias",
"visual.blocks.15.mlp.down_proj",
"visual.blocks.15.mlp.down_proj.bias",
"visual.blocks.15.mlp.gate_proj",
"visual.blocks.15.mlp.gate_proj.bias",
"visual.blocks.15.mlp.up_proj",
"visual.blocks.15.mlp.up_proj.bias",
"visual.blocks.15.norm1",
"visual.blocks.15.norm2",
"visual.blocks.16.attn.k_norm",
"visual.blocks.16.attn.proj",
"visual.blocks.16.attn.proj.bias",
"visual.blocks.16.attn.q_norm",
"visual.blocks.16.attn.qkv",
"visual.blocks.16.attn.qkv.bias",
"visual.blocks.16.mlp.down_proj",
"visual.blocks.16.mlp.down_proj.bias",
"visual.blocks.16.mlp.gate_proj",
"visual.blocks.16.mlp.gate_proj.bias",
"visual.blocks.16.mlp.up_proj",
"visual.blocks.16.mlp.up_proj.bias",
"visual.blocks.16.norm1",
"visual.blocks.16.norm2",
"visual.blocks.17.attn.k_norm",
"visual.blocks.17.attn.proj",
"visual.blocks.17.attn.proj.bias",
"visual.blocks.17.attn.q_norm",
"visual.blocks.17.attn.qkv",
"visual.blocks.17.attn.qkv.bias",
"visual.blocks.17.mlp.down_proj",
"visual.blocks.17.mlp.down_proj.bias",
"visual.blocks.17.mlp.gate_proj",
"visual.blocks.17.mlp.gate_proj.bias",
"visual.blocks.17.mlp.up_proj",
"visual.blocks.17.mlp.up_proj.bias",
"visual.blocks.17.norm1",
"visual.blocks.17.norm2",
"visual.blocks.18.attn.k_norm",
"visual.blocks.18.attn.proj",
"visual.blocks.18.attn.proj.bias",
"visual.blocks.18.attn.q_norm",
"visual.blocks.18.attn.qkv",
"visual.blocks.18.attn.qkv.bias",
"visual.blocks.18.mlp.down_proj",
"visual.blocks.18.mlp.down_proj.bias",
"visual.blocks.18.mlp.gate_proj",
"visual.blocks.18.mlp.gate_proj.bias",
"visual.blocks.18.mlp.up_proj",
"visual.blocks.18.mlp.up_proj.bias",
"visual.blocks.18.norm1",
"visual.blocks.18.norm2",
"visual.blocks.19.attn.k_norm",
"visual.blocks.19.attn.proj",
"visual.blocks.19.attn.proj.bias",
"visual.blocks.19.attn.q_norm",
"visual.blocks.19.attn.qkv",
"visual.blocks.19.attn.qkv.bias",
"visual.blocks.19.mlp.down_proj",
"visual.blocks.19.mlp.down_proj.bias",
"visual.blocks.19.mlp.gate_proj",
"visual.blocks.19.mlp.gate_proj.bias",
"visual.blocks.19.mlp.up_proj",
"visual.blocks.19.mlp.up_proj.bias",
"visual.blocks.19.norm1",
"visual.blocks.19.norm2",
"visual.blocks.2.attn.k_norm",
"visual.blocks.2.attn.proj",
"visual.blocks.2.attn.proj.bias",
"visual.blocks.2.attn.q_norm",
"visual.blocks.2.attn.qkv",
"visual.blocks.2.attn.qkv.bias",
"visual.blocks.2.mlp.down_proj",
"visual.blocks.2.mlp.down_proj.bias",
"visual.blocks.2.mlp.gate_proj",
"visual.blocks.2.mlp.gate_proj.bias",
"visual.blocks.2.mlp.up_proj",
"visual.blocks.2.mlp.up_proj.bias",
"visual.blocks.2.norm1",
"visual.blocks.2.norm2",
"visual.blocks.20.attn.k_norm",
"visual.blocks.20.attn.proj",
"visual.blocks.20.attn.proj.bias",
"visual.blocks.20.attn.q_norm",
"visual.blocks.20.attn.qkv",
"visual.blocks.20.attn.qkv.bias",
"visual.blocks.20.mlp.down_proj",
"visual.blocks.20.mlp.down_proj.bias",
"visual.blocks.20.mlp.gate_proj",
"visual.blocks.20.mlp.gate_proj.bias",
"visual.blocks.20.mlp.up_proj",
"visual.blocks.20.mlp.up_proj.bias",
"visual.blocks.20.norm1",
"visual.blocks.20.norm2",
"visual.blocks.21.attn.k_norm",
"visual.blocks.21.attn.proj",
"visual.blocks.21.attn.proj.bias",
"visual.blocks.21.attn.q_norm",
"visual.blocks.21.attn.qkv",
"visual.blocks.21.attn.qkv.bias",
"visual.blocks.21.mlp.down_proj",
"visual.blocks.21.mlp.down_proj.bias",
"visual.blocks.21.mlp.gate_proj",
"visual.blocks.21.mlp.gate_proj.bias",
"visual.blocks.21.mlp.up_proj",
"visual.blocks.21.mlp.up_proj.bias",
"visual.blocks.21.norm1",
"visual.blocks.21.norm2",
"visual.blocks.22.attn.k_norm",
"visual.blocks.22.attn.proj",
"visual.blocks.22.attn.proj.bias",
"visual.blocks.22.attn.q_norm",
"visual.blocks.22.attn.qkv",
"visual.blocks.22.attn.qkv.bias",
"visual.blocks.22.mlp.down_proj",
"visual.blocks.22.mlp.down_proj.bias",
"visual.blocks.22.mlp.gate_proj",
"visual.blocks.22.mlp.gate_proj.bias",
"visual.blocks.22.mlp.up_proj",
"visual.blocks.22.mlp.up_proj.bias",
"visual.blocks.22.norm1",
"visual.blocks.22.norm2",
"visual.blocks.23.attn.k_norm",
"visual.blocks.23.attn.proj",
"visual.blocks.23.attn.proj.bias",
"visual.blocks.23.attn.q_norm",
"visual.blocks.23.attn.qkv",
"visual.blocks.23.attn.qkv.bias",
"visual.blocks.23.mlp.down_proj",
"visual.blocks.23.mlp.down_proj.bias",
"visual.blocks.23.mlp.gate_proj",
"visual.blocks.23.mlp.gate_proj.bias",
"visual.blocks.23.mlp.up_proj",
"visual.blocks.23.mlp.up_proj.bias",
"visual.blocks.23.norm1",
"visual.blocks.23.norm2",
"visual.blocks.3.attn.k_norm",
"visual.blocks.3.attn.proj",
"visual.blocks.3.attn.proj.bias",
"visual.blocks.3.attn.q_norm",
"visual.blocks.3.attn.qkv",
"visual.blocks.3.attn.qkv.bias",
"visual.blocks.3.mlp.down_proj",
"visual.blocks.3.mlp.down_proj.bias",
"visual.blocks.3.mlp.gate_proj",
"visual.blocks.3.mlp.gate_proj.bias",
"visual.blocks.3.mlp.up_proj",
"visual.blocks.3.mlp.up_proj.bias",
"visual.blocks.3.norm1",
"visual.blocks.3.norm2",
"visual.blocks.4.attn.k_norm",
"visual.blocks.4.attn.proj",
"visual.blocks.4.attn.proj.bias",
"visual.blocks.4.attn.q_norm",
"visual.blocks.4.attn.qkv",
"visual.blocks.4.attn.qkv.bias",
"visual.blocks.4.mlp.down_proj",
"visual.blocks.4.mlp.down_proj.bias",
"visual.blocks.4.mlp.gate_proj",
"visual.blocks.4.mlp.gate_proj.bias",
"visual.blocks.4.mlp.up_proj",
"visual.blocks.4.mlp.up_proj.bias",
"visual.blocks.4.norm1",
"visual.blocks.4.norm2",
"visual.blocks.5.attn.k_norm",
"visual.blocks.5.attn.proj",
"visual.blocks.5.attn.proj.bias",
"visual.blocks.5.attn.q_norm",
"visual.blocks.5.attn.qkv",
"visual.blocks.5.attn.qkv.bias",
"visual.blocks.5.mlp.down_proj",
"visual.blocks.5.mlp.down_proj.bias",
"visual.blocks.5.mlp.gate_proj",
"visual.blocks.5.mlp.gate_proj.bias",
"visual.blocks.5.mlp.up_proj",
"visual.blocks.5.mlp.up_proj.bias",
"visual.blocks.5.norm1",
"visual.blocks.5.norm2",
"visual.blocks.6.attn.k_norm",
"visual.blocks.6.attn.proj",
"visual.blocks.6.attn.proj.bias",
"visual.blocks.6.attn.q_norm",
"visual.blocks.6.attn.qkv",
"visual.blocks.6.attn.qkv.bias",
"visual.blocks.6.mlp.down_proj",
"visual.blocks.6.mlp.down_proj.bias",
"visual.blocks.6.mlp.gate_proj",
"visual.blocks.6.mlp.gate_proj.bias",
"visual.blocks.6.mlp.up_proj",
"visual.blocks.6.mlp.up_proj.bias",
"visual.blocks.6.norm1",
"visual.blocks.6.norm2",
"visual.blocks.7.attn.k_norm",
"visual.blocks.7.attn.proj",
"visual.blocks.7.attn.proj.bias",
"visual.blocks.7.attn.q_norm",
"visual.blocks.7.attn.qkv",
"visual.blocks.7.attn.qkv.bias",
"visual.blocks.7.mlp.down_proj",
"visual.blocks.7.mlp.down_proj.bias",
"visual.blocks.7.mlp.gate_proj",
"visual.blocks.7.mlp.gate_proj.bias",
"visual.blocks.7.mlp.up_proj",
"visual.blocks.7.mlp.up_proj.bias",
"visual.blocks.7.norm1",
"visual.blocks.7.norm2",
"visual.blocks.8.attn.k_norm",
"visual.blocks.8.attn.proj",
"visual.blocks.8.attn.proj.bias",
"visual.blocks.8.attn.q_norm",
"visual.blocks.8.attn.qkv",
"visual.blocks.8.attn.qkv.bias",
"visual.blocks.8.mlp.down_proj",
"visual.blocks.8.mlp.down_proj.bias",
"visual.blocks.8.mlp.gate_proj",
"visual.blocks.8.mlp.gate_proj.bias",
"visual.blocks.8.mlp.up_proj",
"visual.blocks.8.mlp.up_proj.bias",
"visual.blocks.8.norm1",
"visual.blocks.8.norm2",
"visual.blocks.9.attn.k_norm",
"visual.blocks.9.attn.proj",
"visual.blocks.9.attn.proj.bias",
"visual.blocks.9.attn.q_norm",
"visual.blocks.9.attn.qkv",
"visual.blocks.9.attn.qkv.bias",
"visual.blocks.9.mlp.down_proj",
"visual.blocks.9.mlp.down_proj.bias",
"visual.blocks.9.mlp.gate_proj",
"visual.blocks.9.mlp.gate_proj.bias",
"visual.blocks.9.mlp.up_proj",
"visual.blocks.9.mlp.up_proj.bias",
"visual.blocks.9.norm1",
"visual.blocks.9.norm2",
"visual.downsample",
"visual.downsample.bias",
"visual.merger.down_proj",
"visual.merger.gate_proj",
"visual.merger.post_projection_norm",
"visual.merger.post_projection_norm.bias",
"visual.merger.proj",
"visual.merger.up_proj",
"visual.patch_embed.proj",
"visual.patch_embed.proj.bias",
"visual.post_layernorm",
"weights_proj"
],
"quant_method": "fp8"
},
"tokenizer_config": {
"eos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>"
}
},
"createdAt": "2026-08-26T21:09:20.000Z",
"disabled": false,
"downloads": 49224,
"gated": false,
"id": "dealignai/GLM-5.3-Flash-UNCENSORED-FP8",
"lastModified": "2026-09-19T16:32:29.000Z",
"likes": 126,
"model-index": null,
"modelId": "dealignai/GLM-5.3-Flash-UNCENSORED-FP8",
"private": false,
"safetensors": {
"parameters": {
"BF16": 6926096640,
"F32": 295518,
"F8_E4M3": 314396639232
},
"total": 321323031390
},
"sha": "d5822b068da8ddb301665b48c58718e6e18a2c3a",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "dealign_logo.png"
},
{
"rfilename": "dealign_mascot.png"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "model-00001-of-00062.safetensors"
},
{
"rfilename": "model-00002-of-00062.safetensors"
},
{
"rfilename": "model-00003-of-00062.safetensors"
},
{
"rfilename": "model-00004-of-00062.safetensors"
},
{
"rfilename": "model-00005-of-00062.safetensors"
},
{
"rfilename": "model-00006-of-00062.safetensors"
},
{
"rfilename": "model-00007-of-00062.safetensors"
},
{
"rfilename": "model-00008-of-00062.safetensors"
},
{
"rfilename": "model-00009-of-00062.safetensors"
},
{
"rfilename": "model-00010-of-00062.safetensors"
},
{
"rfilename": "model-00011-of-00062.safetensors"
},
{
"rfilename": "model-00012-of-00062.safetensors"
},
{
"rfilename": "model-00013-of-00062.safetensors"
},
{
"rfilename": "model-00014-of-00062.safetensors"
},
{
"rfilename": "model-00015-of-00062.safetensors"
},
{
"rfilename": "model-00016-of-00062.safetensors"
},
{
"rfilename": "model-00017-of-00062.safetensors"
},
{
"rfilename": "model-00018-of-00062.safetensors"
},
{
"rfilename": "model-00019-of-00062.safetensors"
},
{
"rfilename": "model-00020-of-00062.safetensors"
},
{
"rfilename": "model-00021-of-00062.safetensors"
},
{
"rfilename": "model-00022-of-00062.safetensors"
},
{
"rfilename": "model-00023-of-00062.safetensors"
},
{
"rfilename": "model-00024-of-00062.safetensors"
},
{
"rfilename": "model-00025-of-00062.safetensors"
},
{
"rfilename": "model-00026-of-00062.safetensors"
},
{
"rfilename": "model-00027-of-00062.safetensors"
},
{
"rfilename": "model-00028-of-00062.safetensors"
},
{
"rfilename": "model-00029-of-00062.safetensors"
},
{
"rfilename": "model-00030-of-00062.safetensors"
},
{
"rfilename": "model-00031-of-00062.safetensors"
},
{
"rfilename": "model-00032-of-00062.safetensors"
},
{
"rfilename": "model-00033-of-00062.safetensors"
},
{
"rfilename": "model-00034-of-00062.safetensors"
},
{
"rfilename": "model-00035-of-00062.safetensors"
},
{
"rfilename": "model-00036-of-00062.safetensors"
},
{
"rfilename": "model-00037-of-00062.safetensors"
},
{
"rfilename": "model-00038-of-00062.safetensors"
},
{
"rfilename": "model-00039-of-00062.safetensors"
},
{
"rfilename": "model-00040-of-00062.safetensors"
},
{
"rfilename": "model-00041-of-00062.safetensors"
},
{
"rfilename": "model-00042-of-00062.safetensors"
},
{
"rfilename": "model-00043-of-00062.safetensors"
},
{
"rfilename": "model-00044-of-00062.safetensors"
},
{
"rfilename": "model-00045-of-00062.safetensors"
},
{
"rfilename": "model-00046-of-00062.safetensors"
},
{
"rfilename": "model-00047-of-00062.safetensors"
},
{
"rfilename": "model-00048-of-00062.safetensors"
},
{
"rfilename": "model-00049-of-00062.safetensors"
},
{
"rfilename": "model-00050-of-00062.safetensors"
},
{
"rfilename": "model-00051-of-00062.safetensors"
},
{
"rfilename": "model-00052-of-00062.safetensors"
},
{
"rfilename": "model-00053-of-00062.safetensors"
},
{
"rfilename": "model-00054-of-00062.safetensors"
},
{
"rfilename": "model-00055-of-00062.safetensors"
},
{
"rfilename": "model-00056-of-00062.safetensors"
},
{
"rfilename": "model-00057-of-00062.safetensors"
},
{
"rfilename": "model-00058-of-00062.safetensors"
},
{
"rfilename": "model-00059-of-00062.safetensors"
},
{
"rfilename": "model-00060-of-00062.safetensors"
},
{
"rfilename": "model-00061-of-00062.safetensors"
},
{
"rfilename": "model-00062-of-00062.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "processor_config.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
}
],
"spaces": [
"tardellirs/model-pulse",
"aquanode/gpu-vram-calculator"
],
"tags": [
"safetensors",
"glm5_next",
"abliterated",
"uncensored",
"crack",
"glm",
"moe",
"fp8",
"vision",
"mtp",
"en",
"base_model:zai-org/GLM-5.3-Flash",
"base_model:quantized:zai-org/GLM-5.3-Flash",
"license:mit",
"region:us"
],
"usedStorage": 505375369250
} | ||||||||
| likes | 126receipt
What the source handed over{
"_asked": "dealignai/GLM-5.3-Flash-UNCENSORED-FP8",
"_id": "6a8f5600e8e799f3299d529f",
"author": "dealignai",
"cardData": {
"base_model": [
"zai-org/GLM-5.3-Flash"
],
"language": [
"en"
],
"license": "mit",
"tags": [
"abliterated",
"uncensored",
"crack",
"glm",
"moe",
"fp8",
"vision",
"mtp"
],
"thumbnail": "dealign_mascot.png"
},
"config": {
"architectures": [
"Glm5NextForConditionalGeneration"
],
"chat_template_jinja": "[gMASK]<sop>\n{%- set effective_reasoning_effort = reasoning_effort if reasoning_effort is defined and reasoning_effort in ['low', 'high'] else 'max' -%}\n{%- if effective_reasoning_effort is not none -%}<|system|>Reasoning Effort: {{ effective_reasoning_effort | capitalize }}{%- endif -%}\n{%- set clear_thinking = clear_thinking if clear_thinking is defined else true -%}\n{%- if tools -%}\n{%- macro tool_to_json(tool) -%}\n {%- set ns_tool = namespace(first=true) -%}\n {{ '{' -}}\n {%- for k, v in tool.items() -%}\n {%- if k != 'defer_loading' and k != 'strict' -%}\n {%- if not ns_tool.first -%}{{- ', ' -}}{%- endif -%}\n {%- set ns_tool.first = false -%}\n \"{{ k }}\": {{ v | tojson(ensure_ascii=False) }}\n {%- endif -%}\n {%- endfor -%}\n {{- '}' -}}\n{%- endmacro -%}\n{%- macro tool_references_to_response(refs) -%}\n {{- '<tool_response><tools>\\n' -}}\n {%- for tr in refs -%}\n {%- for tool in tools -%}\n {%- if 'function' in tool -%}\n {%- set tool = tool['function'] -%}\n {%- endif -%}\n {%- if tool.name == tr.name -%}\n {{- tool_to_json(tool) + '\\n' -}}\n {%- endif -%}\n {%- endfor -%}\n {%- endfor -%}\n {{- '</tools></tool_response>' -}}\n{%- endmacro -%}\n<|system|>\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>\n{% for tool in tools %}\n{%- if 'function' in tool -%}\n {%- set tool = tool['function'] -%}\n{%- endif -%}\n{% if tool.defer_loading is not defined or not tool.defer_loading %}\n{{ tool_to_json(tool) }}\n{% endif %}\n{% endfor %}\n</tools>\n\nFor each function call, output the function name and arguments within the following XML format:\n<tool_call>{function-name}<arg_key>{arg-key-1}</arg_key><arg_value>{arg-value-1}</arg_value><arg_key>{arg-key-2}</arg_key><arg_value>{arg-value-2}</arg_value>...</tool_call>{%- endif -%}\n{%- macro emit_image() -%}<|begin_of_image|><|image|><|end_of_image|>{%- endmacro -%}\n{%- macro emit_video() -%}<|begin_of_video|><|video|><|end_of_video|>{%- endmacro -%}\n{%- macro emit_audio() -%}<|begin_of_audio|><|end_of_audio|>{%- endmacro -%}\n{%- macro visible_text(content) -%}\n {%- if content is string -%}\n {{- content -}}\n {%- elif content is iterable and content is not mapping -%}\n {%- for item in content -%}\n {%- if item is mapping and item.type == 'text' -%}\n {{- item.text -}}\n {%- elif item is string -%}\n {{- item -}}\n {%- elif item is mapping and item.type in ['image', 'image_url'] -%}\n {{- emit_image() -}}\n {%- elif item is mapping and item.type in ['video', 'video_url'] -%}\n {{- emit_video() -}}\n {%- elif item is mapping and item.type in ['audio', 'audio_url', 'input_audio'] -%}\n {{- emit_audio() -}}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {{- content }}\n {%- endif -%}\n{%- endmacro -%}\n{%- macro tool_response(text) -%}\n{{- '<tool_response>' + text + '</tool_response>' -}}\n{%- endmacro -%}\n{%- macro render_tool_response(m) -%}\n{%- if m.content is string -%}\n {{- tool_response(m.content) -}}\n{%- elif m.content and m.content is not mapping and m.content.0.type == \"tool_reference\" -%}\n {{- tool_references_to_response(m.content) -}}\n{%- elif is_list_of_outputs(m) -%}\n {%- for tr in m.content -%}\n {%- if tr.output is iterable and tr.output is not string and tr.output is not mapping and tr.output and tr.output.0.type == \"tool_reference\" -%}\n {{- tool_references_to_response(tr.output) -}}\n {%- else -%}\n {{- tool_response(visible_text(tr.output)) -}}\n {%- endif -%}\n {%- endfor -%}\n{%- else -%}\n {{- tool_response(visible_text(m.content)) -}}\n{%- endif -%}\n{%- endmacro -%}\n{%- macro id_of(obj) -%}\n {%- if obj.tool_call_id -%}\n {{- obj.tool_call_id -}}\n {%- elif obj.id -%}\n {{- obj.id -}}\n {%- endif -%}\n{%- endmacro -%}\n{%- macro is_list_of_outputs(m) -%}\n {%- if m.content and m.content.0.output is defined -%}1{%- endif -%}\n{%- endmacro -%}\n{%- macro has_dup_tool_result_id(lo, hi, target) -%}\n {%- set ns_cnt = namespace(n=0) -%}\n {%- for k in range(lo, hi + 1) -%}\n {%- set m = messages[k] -%}\n {%- if is_list_of_outputs(m) -%}\n {%- for entry in m.content -%}\n {%- if id_of(entry) == target -%}\n {%- set ns_cnt.n = ns_cnt.n + 1 -%}\n {%- endif -%}\n {%- endfor -%}\n {%- elif id_of(m) == target -%}\n {%- set ns_cnt.n = ns_cnt.n + 1 -%}\n {%- endif -%}\n {%- if ns_cnt.n > 1 -%}{%- break -%}{%- endif -%}\n {%- endfor -%}\n {%- if ns_cnt.n > 1 -%}1{%- endif -%}\n{%- endmacro -%}\n{%- macro tc_id_exists(tcs, target) -%}\n {%- set ns_f = namespace(found=false) -%}\n {%- for tc in tcs -%}\n {%- if id_of(tc) == target -%}\n {%- set ns_f.found = true -%}\n {%- break -%}\n {%- endif -%}\n {%- endfor -%}\n {%- if ns_f.found -%}1{%- endif -%}\n{%- endmacro -%}\n{%- set ns = namespace(last_user_index=-1) -%}\n{%- for m in messages %}\n {%- if m.role == 'user' %}\n {%- set ns.last_user_index = loop.index0 -%}\n {%- endif %}\n{%- endfor %}\n{%- for m in messages -%}\n{%- if m.role == 'user' -%}<|user|>{{ visible_text(m.content) }}\n{%- elif m.role == 'assistant' -%}\n<|assistant|>\n{%- set content = visible_text(m.content) %}\n{%- if m.reasoning_content is string %}\n {%- set reasoning_content = m.reasoning_content %}\n{%- elif '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}\n {%- set content = content.split('</think>')[-1] %}\n{%- endif %}\n{%- if (not clear_thinking or loop.index0 > ns.last_user_index) and reasoning_content is defined -%}\n{{ '<think>' + reasoning_content + '</think>'}}\n{%- else -%}\n{{ '<think></think>' }}\n{%- endif -%}\n{%- if content.strip() -%}\n{{ content.strip() }}\n{%- endif -%}\n{% if m.tool_calls %}\n{% for tc in m.tool_calls %}\n{%- if tc.function %}\n {%- set tc = tc.function %}\n{%- endif %}\n{{- '<tool_call>' + tc.name -}}\n{% set _args = tc.arguments %}{% for k, v in _args.items() %}<arg_key>{{ k }}</arg_key><arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>{% endfor %}</tool_call>{% endfor %}\n{% endif %}\n{%- elif m.role == 'tool' -%}\n{%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|observation|>' -}}\n {%- set block_start = loop.index0 -%}\n {%- set ns_blk = namespace(end=block_start) -%}\n {%- for j in range(block_start, messages|length) -%}\n {%- if messages[j].role == 'tool' -%}\n {%- set ns_blk.end = j -%}\n {%- else -%}\n {%- break -%}\n {%- endif -%}\n {%- endfor -%}\n {%- set ns_a = namespace(tool_calls=none) -%}\n {%- if block_start > 0 and messages[block_start - 1].role == 'assistant' and messages[block_start - 1].tool_calls -%}\n {%- set ns_a.tool_calls = messages[block_start - 1].tool_calls -%}\n {%- endif -%}\n {%- set ns_chk = namespace(can_sort=true) -%}\n {%- if not ns_a.tool_calls -%}\n {%- set ns_chk.can_sort = false -%}\n {%- else -%}\n {%- for k in range(block_start, ns_blk.end + 1) -%}\n {%- set m = messages[k] -%}\n {%- if is_list_of_outputs(m) -%}\n {%- for entry in m.content -%}\n {%- set eid = id_of(entry) -%}\n {%- if not eid -%}\n {%- set ns_chk.can_sort = false -%}\n {%- elif has_dup_tool_result_id(block_start, ns_blk.end, eid) -%}\n {%- set ns_chk.can_sort = false -%}\n {%- elif not tc_id_exists(ns_a.tool_calls, eid) -%}\n {%- set ns_chk.can_sort = false -%}\n {%- endif -%}\n {%- endfor -%}\n {%- else -%}\n {%- set tk_id = id_of(m) -%}\n {%- if not tk_id -%}\n {%- set ns_chk.can_sort = false -%}\n {%- elif has_dup_tool_result_id(block_start, ns_blk.end, tk_id) -%}\n {%- set ns_chk.can_sort = false -%}\n {%- elif not tc_id_exists(ns_a.tool_calls, tk_id) -%}\n {%- set ns_chk.can_sort = false -%}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n {%- for i in range(ns_a.tool_calls | length) -%}\n {%- set tc_id = id_of(ns_a.tool_calls[i]) -%}\n {%- if not tc_id -%}\n {%- set ns_chk.can_sort = false -%}\n {%- endif -%}\n {%- for j in range(i + 1, ns_a.tool_calls | length) -%}\n {%- if id_of(ns_a.tool_calls[j]) == tc_id -%}\n {%- set ns_chk.can_sort = false -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endfor -%}\n {%- endif -%}\n {%- if ns_chk.can_sort -%}\n {%- for tc in ns_a.tool_calls -%}\n {%- set tc_id = id_of(tc) -%}\n {%- for k in range(block_start, ns_blk.end + 1) -%}\n {%- set m = messages[k] -%}\n {%- if is_list_of_outputs(m) -%}\n {%- for entry in m.content -%}\n {%- set eid = id_of(entry) -%}\n {%- if eid == tc_id -%}\n {%- if entry.output is iterable and entry.output is not string and entry.output is not mapping and entry.output and entry.output.0.type == \"tool_reference\" -%}\n {{- tool_references_to_response(entry.output) -}}\n {%- else -%}\n {{- tool_response(visible_text(entry.output)) -}}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n{%- else -%}\n {%- set tk_id = id_of(m) -%}\n {%- if tk_id == tc_id -%}\n {{- render_tool_response(m) -}}\n {%- endif -%}\n {%- endif -%}\n {%- endfor -%}\n {%- endfor -%}\n {%- else -%}\n {%- for k in range(block_start, ns_blk.end + 1) -%}\n {{- render_tool_response(messages[k]) -}}\n {%- endfor -%}\n {%- endif -%}\n{% endif -%}\n{%- elif m.role == 'system' -%}\n<|system|>{{ visible_text(m.content) }}\n{%- endif -%}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n <|assistant|>{{- '<think>' -}}\n{%- endif -%}\n",
"model_type": "glm5_next",
"quantization_config": {
"modules_to_not_convert": [
"attn_mha",
"attn_mqa",
"dt_bias",
"hyper_connection",
"lm_head",
"mapping_proj",
"model.embed_tokens",
"model.layers.0.hc_attn_base",
"model.layers.0.hc_attn_fn",
"model.layers.0.hc_attn_scale",
"model.layers.0.hc_ffn_base",
"model.layers.0.hc_ffn_fn",
"model.layers.0.hc_ffn_scale",
"model.layers.0.input_layernorm",
"model.layers.0.post_attention_layernorm",
"model.layers.0.self_attn.A_log",
"model.layers.0.self_attn.b_proj",
"model.layers.0.self_attn.dt_bias",
"model.layers.0.self_attn.f_a_proj",
"model.layers.0.self_attn.f_b_proj",
"model.layers.0.self_attn.fused_qkvbfg_a_proj",
"model.layers.0.self_attn.g_a_proj",
"model.layers.0.self_attn.g_b_proj",
"model.layers.0.self_attn.k_conv1d",
"model.layers.0.self_attn.k_proj",
"model.layers.0.self_attn.o_norm",
"model.layers.0.self_attn.o_proj",
"model.layers.0.self_attn.q_conv1d",
"model.layers.0.self_attn.q_proj",
"model.layers.0.self_attn.qkv_proj",
"model.layers.0.self_attn.v_conv1d",
"model.layers.0.self_attn.v_proj",
"model.layers.1.hc_attn_base",
"model.layers.1.hc_attn_fn",
"model.layers.1.hc_attn_scale",
"model.layers.1.hc_ffn_base",
"model.layers.1.hc_ffn_fn",
"model.layers.1.hc_ffn_scale",
"model.layers.1.input_layernorm",
"model.layers.1.post_attention_layernorm",
"model.layers.1.self_attn.A_log",
"model.layers.1.self_attn.b_proj",
"model.layers.1.self_attn.dt_bias",
"model.layers.1.self_attn.f_a_proj",
"model.layers.1.self_attn.f_b_proj",
"model.layers.1.self_attn.fused_qkvbfg_a_proj",
"model.layers.1.self_attn.g_a_proj",
"model.layers.1.self_attn.g_b_proj",
"model.layers.1.self_attn.k_conv1d",
"model.layers.1.self_attn.k_proj",
"model.layers.1.self_attn.o_norm",
"model.layers.1.self_attn.o_proj",
"model.layers.1.self_attn.q_conv1d",
"model.layers.1.self_attn.q_proj",
"model.layers.1.self_attn.qkv_proj",
"model.layers.1.self_attn.v_conv1d",
"model.layers.1.self_attn.v_proj",
"model.layers.10.hc_attn_base",
"model.layers.10.hc_attn_fn",
"model.layers.10.hc_attn_scale",
"model.layers.10.hc_ffn_base",
"model.layers.10.hc_ffn_fn",
"model.layers.10.hc_ffn_scale",
"model.layers.10.input_layernorm",
"model.layers.10.mlp.gate",
"model.layers.10.mlp.gate.e_score_correction_bias",
"model.layers.10.post_attention_layernorm",
"model.layers.10.self_attn.A_log",
"model.layers.10.self_attn.b_proj",
"model.layers.10.self_attn.dt_bias",
"model.layers.10.self_attn.f_a_proj",
"model.layers.10.self_attn.f_b_proj",
"model.layers.10.self_attn.fused_qkvbfg_a_proj",
"model.layers.10.self_attn.g_a_proj",
"model.layers.10.self_attn.g_b_proj",
"model.layers.10.self_attn.k_conv1d",
"model.layers.10.self_attn.k_proj",
"model.layers.10.self_attn.o_norm",
"model.layers.10.self_attn.o_proj",
"model.layers.10.self_attn.q_conv1d",
"model.layers.10.self_attn.q_proj",
"model.layers.10.self_attn.qkv_proj",
"model.layers.10.self_attn.v_conv1d",
"model.layers.10.self_attn.v_proj",
"model.layers.11.hc_attn_base",
"model.layers.11.hc_attn_fn",
"model.layers.11.hc_attn_scale",
"model.layers.11.hc_ffn_base",
"model.layers.11.hc_ffn_fn",
"model.layers.11.hc_ffn_scale",
"model.layers.11.input_layernorm",
"model.layers.11.mlp.gate",
"model.layers.11.mlp.gate.e_score_correction_bias",
"model.layers.11.post_attention_layernorm",
"model.layers.11.self_attn.indexer.index_kpool_compress_ape",
"model.layers.11.self_attn.indexer.index_kpool_compress_gate",
"model.layers.11.self_attn.indexer.k_norm",
"model.layers.11.self_attn.indexer.k_norm.bias",
"model.layers.11.self_attn.indexer.weights_proj",
"model.layers.11.self_attn.indexer.wk",
"model.layers.11.self_attn.indexer.wq_b",
"model.layers.11.self_attn.kv_a_layernorm",
"model.layers.11.self_attn.kv_b_proj",
"model.layers.11.self_attn.q_a_layernorm",
"model.layers.12.hc_attn_base",
"model.layers.12.hc_attn_fn",
"model.layers.12.hc_attn_scale",
"model.layers.12.hc_ffn_base",
"model.layers.12.hc_ffn_fn",
"model.layers.12.hc_ffn_scale",
"model.layers.12.input_layernorm",
"model.layers.12.mlp.gate",
"model.layers.12.mlp.gate.e_score_correction_bias",
"model.layers.12.post_attention_layernorm",
"model.layers.12.self_attn.A_log",
"model.layers.12.self_attn.b_proj",
"model.layers.12.self_attn.dt_bias",
"model.layers.12.self_attn.f_a_proj",
"model.layers.12.self_attn.f_b_proj",
"model.layers.12.self_attn.fused_qkvbfg_a_proj",
"model.layers.12.self_attn.g_a_proj",
"model.layers.12.self_attn.g_b_proj",
"model.layers.12.self_attn.k_conv1d",
"model.layers.12.self_attn.k_proj",
"model.layers.12.self_attn.o_norm",
"model.layers.12.self_attn.o_proj",
"model.layers.12.self_attn.q_conv1d",
"model.layers.12.self_attn.q_proj",
"model.layers.12.self_attn.qkv_proj",
"model.layers.12.self_attn.v_conv1d",
"model.layers.12.self_attn.v_proj",
"model.layers.13.hc_attn_base",
"model.layers.13.hc_attn_fn",
"model.layers.13.hc_attn_scale",
"model.layers.13.hc_ffn_base",
"model.layers.13.hc_ffn_fn",
"model.layers.13.hc_ffn_scale",
"model.layers.13.input_layernorm",
"model.layers.13.mlp.gate",
"model.layers.13.mlp.gate.e_score_correction_bias",
"model.layers.13.post_attention_layernorm",
"model.layers.13.self_attn.A_log",
"model.layers.13.self_attn.b_proj",
"model.layers.13.self_attn.dt_bias",
"model.layers.13.self_attn.f_a_proj",
"model.layers.13.self_attn.f_b_proj",
"model.layers.13.self_attn.fused_qkvbfg_a_proj",
"model.layers.13.self_attn.g_a_proj",
"model.layers.13.self_attn.g_b_proj",
"model.layers.13.self_attn.k_conv1d",
"model.layers.13.self_attn.k_proj",
"model.layers.13.self_attn.o_norm",
"model.layers.13.self_attn.o_proj",
"model.layers.13.self_attn.q_conv1d",
"model.layers.13.self_attn.q_proj",
"model.layers.13.self_attn.qkv_proj",
"model.layers.13.self_attn.v_conv1d",
"model.layers.13.self_attn.v_proj",
"model.layers.14.hc_attn_base",
"model.layers.14.hc_attn_fn",
"model.layers.14.hc_attn_scale",
"model.layers.14.hc_ffn_base",
"model.layers.14.hc_ffn_fn",
"model.layers.14.hc_ffn_scale",
"model.layers.14.input_layernorm",
"model.layers.14.mlp.gate",
"model.layers.14.mlp.gate.e_score_correction_bias",
"model.layers.14.post_attention_layernorm",
"model.layers.14.self_attn.A_log",
"model.layers.14.self_attn.b_proj",
"model.layers.14.self_attn.dt_bias",
"model.layers.14.self_attn.f_a_proj",
"model.layers.14.self_attn.f_b_proj",
"model.layers.14.self_attn.fused_qkvbfg_a_proj",
"model.layers.14.self_attn.g_a_proj",
"model.layers.14.self_attn.g_b_proj",
"model.layers.14.self_attn.k_conv1d",
"model.layers.14.self_attn.k_proj",
"model.layers.14.self_attn.o_norm",
"model.layers.14.self_attn.o_proj",
"model.layers.14.self_attn.q_conv1d",
"model.layers.14.self_attn.q_proj",
"model.layers.14.self_attn.qkv_proj",
"model.layers.14.self_attn.v_conv1d",
"model.layers.14.self_attn.v_proj",
"model.layers.15.hc_attn_base",
"model.layers.15.hc_attn_fn",
"model.layers.15.hc_attn_scale",
"model.layers.15.hc_ffn_base",
"model.layers.15.hc_ffn_fn",
"model.layers.15.hc_ffn_scale",
"model.layers.15.input_layernorm",
"model.layers.15.mlp.gate",
"model.layers.15.mlp.gate.e_score_correction_bias",
"model.layers.15.post_attention_layernorm",
"model.layers.15.self_attn.indexer.index_kpool_compress_ape",
"model.layers.15.self_attn.indexer.index_kpool_compress_gate",
"model.layers.15.self_attn.indexer.k_norm",
"model.layers.15.self_attn.indexer.k_norm.bias",
"model.layers.15.self_attn.indexer.weights_proj",
"model.layers.15.self_attn.indexer.wk",
"model.layers.15.self_attn.indexer.wq_b",
"model.layers.15.self_attn.kv_a_layernorm",
"model.layers.15.self_attn.kv_b_proj",
"model.layers.15.self_attn.q_a_layernorm",
"model.layers.16.hc_attn_base",
"model.layers.16.hc_attn_fn",
"model.layers.16.hc_attn_scale",
"model.layers.16.hc_ffn_base",
"model.layers.16.hc_ffn_fn",
"model.layers.16.hc_ffn_scale",
"model.layers.16.input_layernorm",
"model.layers.16.mlp.gate",
"model.layers.16.mlp.gate.e_score_correction_bias",
"model.layers.16.post_attention_layernorm",
"model.layers.16.self_attn.A_log",
"model.layers.16.self_attn.b_proj",
"model.layers.16.self_attn.dt_bias",
"model.layers.16.self_attn.f_a_proj",
"model.layers.16.self_attn.f_b_proj",
"model.layers.16.self_attn.fused_qkvbfg_a_proj",
"model.layers.16.self_attn.g_a_proj",
"model.layers.16.self_attn.g_b_proj",
"model.layers.16.self_attn.k_conv1d",
"model.layers.16.self_attn.k_proj",
"model.layers.16.self_attn.o_norm",
"model.layers.16.self_attn.o_proj",
"model.layers.16.self_attn.q_conv1d",
"model.layers.16.self_attn.q_proj",
"model.layers.16.self_attn.qkv_proj",
"model.layers.16.self_attn.v_conv1d",
"model.layers.16.self_attn.v_proj",
"model.layers.17.hc_attn_base",
"model.layers.17.hc_attn_fn",
"model.layers.17.hc_attn_scale",
"model.layers.17.hc_ffn_base",
"model.layers.17.hc_ffn_fn",
"model.layers.17.hc_ffn_scale",
"model.layers.17.input_layernorm",
"model.layers.17.mlp.gate",
"model.layers.17.mlp.gate.e_score_correction_bias",
"model.layers.17.post_attention_layernorm",
"model.layers.17.self_attn.A_log",
"model.layers.17.self_attn.b_proj",
"model.layers.17.self_attn.dt_bias",
"model.layers.17.self_attn.f_a_proj",
"model.layers.17.self_attn.f_b_proj",
"model.layers.17.self_attn.fused_qkvbfg_a_proj",
"model.layers.17.self_attn.g_a_proj",
"model.layers.17.self_attn.g_b_proj",
"model.layers.17.self_attn.k_conv1d",
"model.layers.17.self_attn.k_proj",
"model.layers.17.self_attn.o_norm",
"model.layers.17.self_attn.o_proj",
"model.layers.17.self_attn.q_conv1d",
"model.layers.17.self_attn.q_proj",
"model.layers.17.self_attn.qkv_proj",
"model.layers.17.self_attn.v_conv1d",
"model.layers.17.self_attn.v_proj",
"model.layers.18.hc_attn_base",
"model.layers.18.hc_attn_fn",
"model.layers.18.hc_attn_scale",
"model.layers.18.hc_ffn_base",
"model.layers.18.hc_ffn_fn",
"model.layers.18.hc_ffn_scale",
"model.layers.18.input_layernorm",
"model.layers.18.mlp.gate",
"model.layers.18.mlp.gate.e_score_correction_bias",
"model.layers.18.post_attention_layernorm",
"model.layers.18.self_attn.A_log",
"model.layers.18.self_attn.b_proj",
"model.layers.18.self_attn.dt_bias",
"model.layers.18.self_attn.f_a_proj",
"model.layers.18.self_attn.f_b_proj",
"model.layers.18.self_attn.fused_qkvbfg_a_proj",
"model.layers.18.self_attn.g_a_proj",
"model.layers.18.self_attn.g_b_proj",
"model.layers.18.self_attn.k_conv1d",
"model.layers.18.self_attn.k_proj",
"model.layers.18.self_attn.o_norm",
"model.layers.18.self_attn.o_proj",
"model.layers.18.self_attn.q_conv1d",
"model.layers.18.self_attn.q_proj",
"model.layers.18.self_attn.qkv_proj",
"model.layers.18.self_attn.v_conv1d",
"model.layers.18.self_attn.v_proj",
"model.layers.19.hc_attn_base",
"model.layers.19.hc_attn_fn",
"model.layers.19.hc_attn_scale",
"model.layers.19.hc_ffn_base",
"model.layers.19.hc_ffn_fn",
"model.layers.19.hc_ffn_scale",
"model.layers.19.input_layernorm",
"model.layers.19.mlp.gate",
"model.layers.19.mlp.gate.e_score_correction_bias",
"model.layers.19.post_attention_layernorm",
"model.layers.19.self_attn.indexer.index_kpool_compress_ape",
"model.layers.19.self_attn.indexer.index_kpool_compress_gate",
"model.layers.19.self_attn.indexer.k_norm",
"model.layers.19.self_attn.indexer.k_norm.bias",
"model.layers.19.self_attn.indexer.weights_proj",
"model.layers.19.self_attn.indexer.wk",
"model.layers.19.self_attn.indexer.wq_b",
"model.layers.19.self_attn.kv_a_layernorm",
"model.layers.19.self_attn.kv_b_proj",
"model.layers.19.self_attn.q_a_layernorm",
"model.layers.2.hc_attn_base",
"model.layers.2.hc_attn_fn",
"model.layers.2.hc_attn_scale",
"model.layers.2.hc_ffn_base",
"model.layers.2.hc_ffn_fn",
"model.layers.2.hc_ffn_scale",
"model.layers.2.input_layernorm",
"model.layers.2.post_attention_layernorm",
"model.layers.2.self_attn.A_log",
"model.layers.2.self_attn.b_proj",
"model.layers.2.self_attn.dt_bias",
"model.layers.2.self_attn.f_a_proj",
"model.layers.2.self_attn.f_b_proj",
"model.layers.2.self_attn.fused_qkvbfg_a_proj",
"model.layers.2.self_attn.g_a_proj",
"model.layers.2.self_attn.g_b_proj",
"model.layers.2.self_attn.k_conv1d",
"model.layers.2.self_attn.k_proj",
"model.layers.2.self_attn.o_norm",
"model.layers.2.self_attn.o_proj",
"model.layers.2.self_attn.q_conv1d",
"model.layers.2.self_attn.q_proj",
"model.layers.2.self_attn.qkv_proj",
"model.layers.2.self_attn.v_conv1d",
"model.layers.2.self_attn.v_proj",
"model.layers.20.hc_attn_base",
"model.layers.20.hc_attn_fn",
"model.layers.20.hc_attn_scale",
"model.layers.20.hc_ffn_base",
"model.layers.20.hc_ffn_fn",
"model.layers.20.hc_ffn_scale",
"model.layers.20.input_layernorm",
"model.layers.20.mlp.gate",
"model.layers.20.mlp.gate.e_score_correction_bias",
"model.layers.20.post_attention_layernorm",
"model.layers.20.self_attn.A_log",
"model.layers.20.self_attn.b_proj",
"model.layers.20.self_attn.dt_bias",
"model.layers.20.self_attn.f_a_proj",
"model.layers.20.self_attn.f_b_proj",
"model.layers.20.self_attn.fused_qkvbfg_a_proj",
"model.layers.20.self_attn.g_a_proj",
"model.layers.20.self_attn.g_b_proj",
"model.layers.20.self_attn.k_conv1d",
"model.layers.20.self_attn.k_proj",
"model.layers.20.self_attn.o_norm",
"model.layers.20.self_attn.o_proj",
"model.layers.20.self_attn.q_conv1d",
"model.layers.20.self_attn.q_proj",
"model.layers.20.self_attn.qkv_proj",
"model.layers.20.self_attn.v_conv1d",
"model.layers.20.self_attn.v_proj",
"model.layers.21.hc_attn_base",
"model.layers.21.hc_attn_fn",
"model.layers.21.hc_attn_scale",
"model.layers.21.hc_ffn_base",
"model.layers.21.hc_ffn_fn",
"model.layers.21.hc_ffn_scale",
"model.layers.21.input_layernorm",
"model.layers.21.mlp.gate",
"model.layers.21.mlp.gate.e_score_correction_bias",
"model.layers.21.post_attention_layernorm",
"model.layers.21.self_attn.A_log",
"model.layers.21.self_attn.b_proj",
"model.layers.21.self_attn.dt_bias",
"model.layers.21.self_attn.f_a_proj",
"model.layers.21.self_attn.f_b_proj",
"model.layers.21.self_attn.fused_qkvbfg_a_proj",
"model.layers.21.self_attn.g_a_proj",
"model.layers.21.self_attn.g_b_proj",
"model.layers.21.self_attn.k_conv1d",
"model.layers.21.self_attn.k_proj",
"model.layers.21.self_attn.o_norm",
"model.layers.21.self_attn.o_proj",
"model.layers.21.self_attn.q_conv1d",
"model.layers.21.self_attn.q_proj",
"model.layers.21.self_attn.qkv_proj",
"model.layers.21.self_attn.v_conv1d",
"model.layers.21.self_attn.v_proj",
"model.layers.22.hc_attn_base",
"model.layers.22.hc_attn_fn",
"model.layers.22.hc_attn_scale",
"model.layers.22.hc_ffn_base",
"model.layers.22.hc_ffn_fn",
"model.layers.22.hc_ffn_scale",
"model.layers.22.input_layernorm",
"model.layers.22.mlp.gate",
"model.layers.22.mlp.gate.e_score_correction_bias",
"model.layers.22.post_attention_layernorm",
"model.layers.22.self_attn.A_log",
"model.layers.22.self_attn.b_proj",
"model.layers.22.self_attn.dt_bias",
"model.layers.22.self_attn.f_a_proj",
"model.layers.22.self_attn.f_b_proj",
"model.layers.22.self_attn.fused_qkvbfg_a_proj",
"model.layers.22.self_attn.g_a_proj",
"model.layers.22.self_attn.g_b_proj",
"model.layers.22.self_attn.k_conv1d",
"model.layers.22.self_attn.k_proj",
"model.layers.22.self_attn.o_norm",
"model.layers.22.self_attn.o_proj",
"model.layers.22.self_attn.q_conv1d",
"model.layers.22.self_attn.q_proj",
"model.layers.22.self_attn.qkv_proj",
"model.layers.22.self_attn.v_conv1d",
"model.layers.22.self_attn.v_proj",
"model.layers.23.hc_attn_base",
"model.layers.23.hc_attn_fn",
"model.layers.23.hc_attn_scale",
"model.layers.23.hc_ffn_base",
"model.layers.23.hc_ffn_fn",
"model.layers.23.hc_ffn_scale",
"model.layers.23.input_layernorm",
"model.layers.23.mlp.gate",
"model.layers.23.mlp.gate.e_score_correction_bias",
"model.layers.23.post_attention_layernorm",
"model.layers.23.self_attn.indexer.index_kpool_compress_ape",
"model.layers.23.self_attn.indexer.index_kpool_compress_gate",
"model.layers.23.self_attn.indexer.k_norm",
"model.layers.23.self_attn.indexer.k_norm.bias",
"model.layers.23.self_attn.indexer.weights_proj",
"model.layers.23.self_attn.indexer.wk",
"model.layers.23.self_attn.indexer.wq_b",
"model.layers.23.self_attn.kv_a_layernorm",
"model.layers.23.self_attn.kv_b_proj",
"model.layers.23.self_attn.q_a_layernorm",
"model.layers.24.hc_attn_base",
"model.layers.24.hc_attn_fn",
"model.layers.24.hc_attn_scale",
"model.layers.24.hc_ffn_base",
"model.layers.24.hc_ffn_fn",
"model.layers.24.hc_ffn_scale",
"model.layers.24.input_layernorm",
"model.layers.24.mlp.gate",
"model.layers.24.mlp.gate.e_score_correction_bias",
"model.layers.24.post_attention_layernorm",
"model.layers.24.self_attn.A_log",
"model.layers.24.self_attn.b_proj",
"model.layers.24.self_attn.dt_bias",
"model.layers.24.self_attn.f_a_proj",
"model.layers.24.self_attn.f_b_proj",
"model.layers.24.self_attn.fused_qkvbfg_a_proj",
"model.layers.24.self_attn.g_a_proj",
"model.layers.24.self_attn.g_b_proj",
"model.layers.24.self_attn.k_conv1d",
"model.layers.24.self_attn.k_proj",
"model.layers.24.self_attn.o_norm",
"model.layers.24.self_attn.o_proj",
"model.layers.24.self_attn.q_conv1d",
"model.layers.24.self_attn.q_proj",
"model.layers.24.self_attn.qkv_proj",
"model.layers.24.self_attn.v_conv1d",
"model.layers.24.self_attn.v_proj",
"model.layers.25.hc_attn_base",
"model.layers.25.hc_attn_fn",
"model.layers.25.hc_attn_scale",
"model.layers.25.hc_ffn_base",
"model.layers.25.hc_ffn_fn",
"model.layers.25.hc_ffn_scale",
"model.layers.25.input_layernorm",
"model.layers.25.mlp.gate",
"model.layers.25.mlp.gate.e_score_correction_bias",
"model.layers.25.post_attention_layernorm",
"model.layers.25.self_attn.A_log",
"model.layers.25.self_attn.b_proj",
"model.layers.25.self_attn.dt_bias",
"model.layers.25.self_attn.f_a_proj",
"model.layers.25.self_attn.f_b_proj",
"model.layers.25.self_attn.fused_qkvbfg_a_proj",
"model.layers.25.self_attn.g_a_proj",
"model.layers.25.self_attn.g_b_proj",
"model.layers.25.self_attn.k_conv1d",
"model.layers.25.self_attn.k_proj",
"model.layers.25.self_attn.o_norm",
"model.layers.25.self_attn.o_proj",
"model.layers.25.self_attn.q_conv1d",
"model.layers.25.self_attn.q_proj",
"model.layers.25.self_attn.qkv_proj",
"model.layers.25.self_attn.v_conv1d",
"model.layers.25.self_attn.v_proj",
"model.layers.26.hc_attn_base",
"model.layers.26.hc_attn_fn",
"model.layers.26.hc_attn_scale",
"model.layers.26.hc_ffn_base",
"model.layers.26.hc_ffn_fn",
"model.layers.26.hc_ffn_scale",
"model.layers.26.input_layernorm",
"model.layers.26.mlp.gate",
"model.layers.26.mlp.gate.e_score_correction_bias",
"model.layers.26.post_attention_layernorm",
"model.layers.26.self_attn.A_log",
"model.layers.26.self_attn.b_proj",
"model.layers.26.self_attn.dt_bias",
"model.layers.26.self_attn.f_a_proj",
"model.layers.26.self_attn.f_b_proj",
"model.layers.26.self_attn.fused_qkvbfg_a_proj",
"model.layers.26.self_attn.g_a_proj",
"model.layers.26.self_attn.g_b_proj",
"model.layers.26.self_attn.k_conv1d",
"model.layers.26.self_attn.k_proj",
"model.layers.26.self_attn.o_norm",
"model.layers.26.self_attn.o_proj",
"model.layers.26.self_attn.q_conv1d",
"model.layers.26.self_attn.q_proj",
"model.layers.26.self_attn.qkv_proj",
"model.layers.26.self_attn.v_conv1d",
"model.layers.26.self_attn.v_proj",
"model.layers.27.hc_attn_base",
"model.layers.27.hc_attn_fn",
"model.layers.27.hc_attn_scale",
"model.layers.27.hc_ffn_base",
"model.layers.27.hc_ffn_fn",
"model.layers.27.hc_ffn_scale",
"model.layers.27.input_layernorm",
"model.layers.27.mlp.gate",
"model.layers.27.mlp.gate.e_score_correction_bias",
"model.layers.27.post_attention_layernorm",
"model.layers.27.self_attn.indexer.index_kpool_compress_ape",
"model.layers.27.self_attn.indexer.index_kpool_compress_gate",
"model.layers.27.self_attn.indexer.k_norm",
"model.layers.27.self_attn.indexer.k_norm.bias",
"model.layers.27.self_attn.indexer.weights_proj",
"model.layers.27.self_attn.indexer.wk",
"model.layers.27.self_attn.indexer.wq_b",
"model.layers.27.self_attn.kv_a_layernorm",
"model.layers.27.self_attn.kv_b_proj",
"model.layers.27.self_attn.q_a_layernorm",
"model.layers.28.hc_attn_base",
"model.layers.28.hc_attn_fn",
"model.layers.28.hc_attn_scale",
"model.layers.28.hc_ffn_base",
"model.layers.28.hc_ffn_fn",
"model.layers.28.hc_ffn_scale",
"model.layers.28.input_layernorm",
"model.layers.28.mlp.gate",
"model.layers.28.mlp.gate.e_score_correction_bias",
"model.layers.28.post_attention_layernorm",
"model.layers.28.self_attn.A_log",
"model.layers.28.self_attn.b_proj",
"model.layers.28.self_attn.dt_bias",
"model.layers.28.self_attn.f_a_proj",
"model.layers.28.self_attn.f_b_proj",
"model.layers.28.self_attn.fused_qkvbfg_a_proj",
"model.layers.28.self_attn.g_a_proj",
"model.layers.28.self_attn.g_b_proj",
"model.layers.28.self_attn.k_conv1d",
"model.layers.28.self_attn.k_proj",
"model.layers.28.self_attn.o_norm",
"model.layers.28.self_attn.o_proj",
"model.layers.28.self_attn.q_conv1d",
"model.layers.28.self_attn.q_proj",
"model.layers.28.self_attn.qkv_proj",
"model.layers.28.self_attn.v_conv1d",
"model.layers.28.self_attn.v_proj",
"model.layers.29.hc_attn_base",
"model.layers.29.hc_attn_fn",
"model.layers.29.hc_attn_scale",
"model.layers.29.hc_ffn_base",
"model.layers.29.hc_ffn_fn",
"model.layers.29.hc_ffn_scale",
"model.layers.29.input_layernorm",
"model.layers.29.mlp.gate",
"model.layers.29.mlp.gate.e_score_correction_bias",
"model.layers.29.post_attention_layernorm",
"model.layers.29.self_attn.A_log",
"model.layers.29.self_attn.b_proj",
"model.layers.29.self_attn.dt_bias",
"model.layers.29.self_attn.f_a_proj",
"model.layers.29.self_attn.f_b_proj",
"model.layers.29.self_attn.fused_qkvbfg_a_proj",
"model.layers.29.self_attn.g_a_proj",
"model.layers.29.self_attn.g_b_proj",
"model.layers.29.self_attn.k_conv1d",
"model.layers.29.self_attn.k_proj",
"model.layers.29.self_attn.o_norm",
"model.layers.29.self_attn.o_proj",
"model.layers.29.self_attn.q_conv1d",
"model.layers.29.self_attn.q_proj",
"model.layers.29.self_attn.qkv_proj",
"model.layers.29.self_attn.v_conv1d",
"model.layers.29.self_attn.v_proj",
"model.layers.3.hc_attn_base",
"model.layers.3.hc_attn_fn",
"model.layers.3.hc_attn_scale",
"model.layers.3.hc_ffn_base",
"model.layers.3.hc_ffn_fn",
"model.layers.3.hc_ffn_scale",
"model.layers.3.input_layernorm",
"model.layers.3.mlp.gate",
"model.layers.3.mlp.gate.e_score_correction_bias",
"model.layers.3.post_attention_layernorm",
"model.layers.3.self_attn.indexer.index_kpool_compress_ape",
"model.layers.3.self_attn.indexer.index_kpool_compress_gate",
"model.layers.3.self_attn.indexer.k_norm",
"model.layers.3.self_attn.indexer.k_norm.bias",
"model.layers.3.self_attn.indexer.weights_proj",
"model.layers.3.self_attn.indexer.wk",
"model.layers.3.self_attn.indexer.wq_b",
"model.layers.3.self_attn.kv_a_layernorm",
"model.layers.3.self_attn.kv_b_proj",
"model.layers.3.self_attn.q_a_layernorm",
"model.layers.30.hc_attn_base",
"model.layers.30.hc_attn_fn",
"model.layers.30.hc_attn_scale",
"model.layers.30.hc_ffn_base",
"model.layers.30.hc_ffn_fn",
"model.layers.30.hc_ffn_scale",
"model.layers.30.input_layernorm",
"model.layers.30.mlp.gate",
"model.layers.30.mlp.gate.e_score_correction_bias",
"model.layers.30.post_attention_layernorm",
"model.layers.30.self_attn.A_log",
"model.layers.30.self_attn.b_proj",
"model.layers.30.self_attn.dt_bias",
"model.layers.30.self_attn.f_a_proj",
"model.layers.30.self_attn.f_b_proj",
"model.layers.30.self_attn.fused_qkvbfg_a_proj",
"model.layers.30.self_attn.g_a_proj",
"model.layers.30.self_attn.g_b_proj",
"model.layers.30.self_attn.k_conv1d",
"model.layers.30.self_attn.k_proj",
"model.layers.30.self_attn.o_norm",
"model.layers.30.self_attn.o_proj",
"model.layers.30.self_attn.q_conv1d",
"model.layers.30.self_attn.q_proj",
"model.layers.30.self_attn.qkv_proj",
"model.layers.30.self_attn.v_conv1d",
"model.layers.30.self_attn.v_proj",
"model.layers.31.hc_attn_base",
"model.layers.31.hc_attn_fn",
"model.layers.31.hc_attn_scale",
"model.layers.31.hc_ffn_base",
"model.layers.31.hc_ffn_fn",
"model.layers.31.hc_ffn_scale",
"model.layers.31.input_layernorm",
"model.layers.31.mlp.gate",
"model.layers.31.mlp.gate.e_score_correction_bias",
"model.layers.31.post_attention_layernorm",
"model.layers.31.self_attn.indexer.index_kpool_compress_ape",
"model.layers.31.self_attn.indexer.index_kpool_compress_gate",
"model.layers.31.self_attn.indexer.k_norm",
"model.layers.31.self_attn.indexer.k_norm.bias",
"model.layers.31.self_attn.indexer.weights_proj",
"model.layers.31.self_attn.indexer.wk",
"model.layers.31.self_attn.indexer.wq_b",
"model.layers.31.self_attn.kv_a_layernorm",
"model.layers.31.self_attn.kv_b_proj",
"model.layers.31.self_attn.q_a_layernorm",
"model.layers.32.hc_attn_base",
"model.layers.32.hc_attn_fn",
"model.layers.32.hc_attn_scale",
"model.layers.32.hc_ffn_base",
"model.layers.32.hc_ffn_fn",
"model.layers.32.hc_ffn_scale",
"model.layers.32.input_layernorm",
"model.layers.32.mlp.gate",
"model.layers.32.mlp.gate.e_score_correction_bias",
"model.layers.32.post_attention_layernorm",
"model.layers.32.self_attn.A_log",
"model.layers.32.self_attn.b_proj",
"model.layers.32.self_attn.dt_bias",
"model.layers.32.self_attn.f_a_proj",
"model.layers.32.self_attn.f_b_proj",
"model.layers.32.self_attn.fused_qkvbfg_a_proj",
"model.layers.32.self_attn.g_a_proj",
"model.layers.32.self_attn.g_b_proj",
"model.layers.32.self_attn.k_conv1d",
"model.layers.32.self_attn.k_proj",
"model.layers.32.self_attn.o_norm",
"model.layers.32.self_attn.o_proj",
"model.layers.32.self_attn.q_conv1d",
"model.layers.32.self_attn.q_proj",
"model.layers.32.self_attn.qkv_proj",
"model.layers.32.self_attn.v_conv1d",
"model.layers.32.self_attn.v_proj",
"model.layers.33.hc_attn_base",
"model.layers.33.hc_attn_fn",
"model.layers.33.hc_attn_scale",
"model.layers.33.hc_ffn_base",
"model.layers.33.hc_ffn_fn",
"model.layers.33.hc_ffn_scale",
"model.layers.33.input_layernorm",
"model.layers.33.mlp.gate",
"model.layers.33.mlp.gate.e_score_correction_bias",
"model.layers.33.post_attention_layernorm",
"model.layers.33.self_attn.A_log",
"model.layers.33.self_attn.b_proj",
"model.layers.33.self_attn.dt_bias",
"model.layers.33.self_attn.f_a_proj",
"model.layers.33.self_attn.f_b_proj",
"model.layers.33.self_attn.fused_qkvbfg_a_proj",
"model.layers.33.self_attn.g_a_proj",
"model.layers.33.self_attn.g_b_proj",
"model.layers.33.self_attn.k_conv1d",
"model.layers.33.self_attn.k_proj",
"model.layers.33.self_attn.o_norm",
"model.layers.33.self_attn.o_proj",
"model.layers.33.self_attn.q_conv1d",
"model.layers.33.self_attn.q_proj",
"model.layers.33.self_attn.qkv_proj",
"model.layers.33.self_attn.v_conv1d",
"model.layers.33.self_attn.v_proj",
"model.layers.34.hc_attn_base",
"model.layers.34.hc_attn_fn",
"model.layers.34.hc_attn_scale",
"model.layers.34.hc_ffn_base",
"model.layers.34.hc_ffn_fn",
"model.layers.34.hc_ffn_scale",
"model.layers.34.input_layernorm",
"model.layers.34.mlp.gate",
"model.layers.34.mlp.gate.e_score_correction_bias",
"model.layers.34.post_attention_layernorm",
"model.layers.34.self_attn.A_log",
"model.layers.34.self_attn.b_proj",
"model.layers.34.self_attn.dt_bias",
"model.layers.34.self_attn.f_a_proj",
"model.layers.34.self_attn.f_b_proj",
"model.layers.34.self_attn.fused_qkvbfg_a_proj",
"model.layers.34.self_attn.g_a_proj",
"model.layers.34.self_attn.g_b_proj",
"model.layers.34.self_attn.k_conv1d",
"model.layers.34.self_attn.k_proj",
"model.layers.34.self_attn.o_norm",
"model.layers.34.self_attn.o_proj",
"model.layers.34.self_attn.q_conv1d",
"model.layers.34.self_attn.q_proj",
"model.layers.34.self_attn.qkv_proj",
"model.layers.34.self_attn.v_conv1d",
"model.layers.34.self_attn.v_proj",
"model.layers.35.hc_attn_base",
"model.layers.35.hc_attn_fn",
"model.layers.35.hc_attn_scale",
"model.layers.35.hc_ffn_base",
"model.layers.35.hc_ffn_fn",
"model.layers.35.hc_ffn_scale",
"model.layers.35.input_layernorm",
"model.layers.35.mlp.gate",
"model.layers.35.mlp.gate.e_score_correction_bias",
"model.layers.35.post_attention_layernorm",
"model.layers.35.self_attn.indexer.index_kpool_compress_ape",
"model.layers.35.self_attn.indexer.index_kpool_compress_gate",
"model.layers.35.self_attn.indexer.k_norm",
"model.layers.35.self_attn.indexer.k_norm.bias",
"model.layers.35.self_attn.indexer.weights_proj",
"model.layers.35.self_attn.indexer.wk",
"model.layers.35.self_attn.indexer.wq_b",
"model.layers.35.self_attn.kv_a_layernorm",
"model.layers.35.self_attn.kv_b_proj",
"model.layers.35.self_attn.q_a_layernorm",
"model.layers.36.hc_attn_base",
"model.layers.36.hc_attn_fn",
"model.layers.36.hc_attn_scale",
"model.layers.36.hc_ffn_base",
"model.layers.36.hc_ffn_fn",
"model.layers.36.hc_ffn_scale",
"model.layers.36.input_layernorm",
"model.layers.36.mlp.gate",
"model.layers.36.mlp.gate.e_score_correction_bias",
"model.layers.36.post_attention_layernorm",
"model.layers.36.self_attn.A_log",
"model.layers.36.self_attn.b_proj",
"model.layers.36.self_attn.dt_bias",
"model.layers.36.self_attn.f_a_proj",
"model.layers.36.self_attn.f_b_proj",
"model.layers.36.self_attn.fused_qkvbfg_a_proj",
"model.layers.36.self_attn.g_a_proj",
"model.layers.36.self_attn.g_b_proj",
"model.layers.36.self_attn.k_conv1d",
"model.layers.36.self_attn.k_proj",
"model.layers.36.self_attn.o_norm",
"model.layers.36.self_attn.o_proj",
"model.layers.36.self_attn.q_conv1d",
"model.layers.36.self_attn.q_proj",
"model.layers.36.self_attn.qkv_proj",
"model.layers.36.self_attn.v_conv1d",
"model.layers.36.self_attn.v_proj",
"model.layers.37.hc_attn_base",
"model.layers.37.hc_attn_fn",
"model.layers.37.hc_attn_scale",
"model.layers.37.hc_ffn_base",
"model.layers.37.hc_ffn_fn",
"model.layers.37.hc_ffn_scale",
"model.layers.37.input_layernorm",
"model.layers.37.mlp.gate",
"model.layers.37.mlp.gate.e_score_correction_bias",
"model.layers.37.post_attention_layernorm",
"model.layers.37.self_attn.A_log",
"model.layers.37.self_attn.b_proj",
"model.layers.37.self_attn.dt_bias",
"model.layers.37.self_attn.f_a_proj",
"model.layers.37.self_attn.f_b_proj",
"model.layers.37.self_attn.fused_qkvbfg_a_proj",
"model.layers.37.self_attn.g_a_proj",
"model.layers.37.self_attn.g_b_proj",
"model.layers.37.self_attn.k_conv1d",
"model.layers.37.self_attn.k_proj",
"model.layers.37.self_attn.o_norm",
"model.layers.37.self_attn.o_proj",
"model.layers.37.self_attn.q_conv1d",
"model.layers.37.self_attn.q_proj",
"model.layers.37.self_attn.qkv_proj",
"model.layers.37.self_attn.v_conv1d",
"model.layers.37.self_attn.v_proj",
"model.layers.38.hc_attn_base",
"model.layers.38.hc_attn_fn",
"model.layers.38.hc_attn_scale",
"model.layers.38.hc_ffn_base",
"model.layers.38.hc_ffn_fn",
"model.layers.38.hc_ffn_scale",
"model.layers.38.input_layernorm",
"model.layers.38.mlp.gate",
"model.layers.38.mlp.gate.e_score_correction_bias",
"model.layers.38.post_attention_layernorm",
"model.layers.38.self_attn.A_log",
"model.layers.38.self_attn.b_proj",
"model.layers.38.self_attn.dt_bias",
"model.layers.38.self_attn.f_a_proj",
"model.layers.38.self_attn.f_b_proj",
"model.layers.38.self_attn.fused_qkvbfg_a_proj",
"model.layers.38.self_attn.g_a_proj",
"model.layers.38.self_attn.g_b_proj",
"model.layers.38.self_attn.k_conv1d",
"model.layers.38.self_attn.k_proj",
"model.layers.38.self_attn.o_norm",
"model.layers.38.self_attn.o_proj",
"model.layers.38.self_attn.q_conv1d",
"model.layers.38.self_attn.q_proj",
"model.layers.38.self_attn.qkv_proj",
"model.layers.38.self_attn.v_conv1d",
"model.layers.38.self_attn.v_proj",
"model.layers.39.hc_attn_base",
"model.layers.39.hc_attn_fn",
"model.layers.39.hc_attn_scale",
"model.layers.39.hc_ffn_base",
"model.layers.39.hc_ffn_fn",
"model.layers.39.hc_ffn_scale",
"model.layers.39.input_layernorm",
"model.layers.39.mlp.gate",
"model.layers.39.mlp.gate.e_score_correction_bias",
"model.layers.39.post_attention_layernorm",
"model.layers.39.self_attn.indexer.index_kpool_compress_ape",
"model.layers.39.self_attn.indexer.index_kpool_compress_gate",
"model.layers.39.self_attn.indexer.k_norm",
"model.layers.39.self_attn.indexer.k_norm.bias",
"model.layers.39.self_attn.indexer.weights_proj",
"model.layers.39.self_attn.indexer.wk",
"model.layers.39.self_attn.indexer.wq_b",
"model.layers.39.self_attn.kv_a_layernorm",
"model.layers.39.self_attn.kv_b_proj",
"model.layers.39.self_attn.q_a_layernorm",
"model.layers.4.hc_attn_base",
"model.layers.4.hc_attn_fn",
"model.layers.4.hc_attn_scale",
"model.layers.4.hc_ffn_base",
"model.layers.4.hc_ffn_fn",
"model.layers.4.hc_ffn_scale",
"model.layers.4.input_layernorm",
"model.layers.4.mlp.gate",
"model.layers.4.mlp.gate.e_score_correction_bias",
"model.layers.4.post_attention_layernorm",
"model.layers.4.self_attn.A_log",
"model.layers.4.self_attn.b_proj",
"model.layers.4.self_attn.dt_bias",
"model.layers.4.self_attn.f_a_proj",
"model.layers.4.self_attn.f_b_proj",
"model.layers.4.self_attn.fused_qkvbfg_a_proj",
"model.layers.4.self_attn.g_a_proj",
"model.layers.4.self_attn.g_b_proj",
"model.layers.4.self_attn.k_conv1d",
"model.layers.4.self_attn.k_proj",
"model.layers.4.self_attn.o_norm",
"model.layers.4.self_attn.o_proj",
"model.layers.4.self_attn.q_conv1d",
"model.layers.4.self_attn.q_proj",
"model.layers.4.self_attn.qkv_proj",
"model.layers.4.self_attn.v_conv1d",
"model.layers.4.self_attn.v_proj",
"model.layers.40.hc_attn_base",
"model.layers.40.hc_attn_fn",
"model.layers.40.hc_attn_scale",
"model.layers.40.hc_ffn_base",
"model.layers.40.hc_ffn_fn",
"model.layers.40.hc_ffn_scale",
"model.layers.40.input_layernorm",
"model.layers.40.mlp.gate",
"model.layers.40.mlp.gate.e_score_correction_bias",
"model.layers.40.post_attention_layernorm",
"model.layers.40.self_attn.A_log",
"model.layers.40.self_attn.b_proj",
"model.layers.40.self_attn.dt_bias",
"model.layers.40.self_attn.f_a_proj",
"model.layers.40.self_attn.f_b_proj",
"model.layers.40.self_attn.fused_qkvbfg_a_proj",
"model.layers.40.self_attn.g_a_proj",
"model.layers.40.self_attn.g_b_proj",
"model.layers.40.self_attn.k_conv1d",
"model.layers.40.self_attn.k_proj",
"model.layers.40.self_attn.o_norm",
"model.layers.40.self_attn.o_proj",
"model.layers.40.self_attn.q_conv1d",
"model.layers.40.self_attn.q_proj",
"model.layers.40.self_attn.qkv_proj",
"model.layers.40.self_attn.v_conv1d",
"model.layers.40.self_attn.v_proj",
"model.layers.41.hc_attn_base",
"model.layers.41.hc_attn_fn",
"model.layers.41.hc_attn_scale",
"model.layers.41.hc_ffn_base",
"model.layers.41.hc_ffn_fn",
"model.layers.41.hc_ffn_scale",
"model.layers.41.input_layernorm",
"model.layers.41.mlp.gate",
"model.layers.41.mlp.gate.e_score_correction_bias",
"model.layers.41.post_attention_layernorm",
"model.layers.41.self_attn.A_log",
"model.layers.41.self_attn.b_proj",
"model.layers.41.self_attn.dt_bias",
"model.layers.41.self_attn.f_a_proj",
"model.layers.41.self_attn.f_b_proj",
"model.layers.41.self_attn.fused_qkvbfg_a_proj",
"model.layers.41.self_attn.g_a_proj",
"model.layers.41.self_attn.g_b_proj",
"model.layers.41.self_attn.k_conv1d",
"model.layers.41.self_attn.k_proj",
"model.layers.41.self_attn.o_norm",
"model.layers.41.self_attn.o_proj",
"model.layers.41.self_attn.q_conv1d",
"model.layers.41.self_attn.q_proj",
"model.layers.41.self_attn.qkv_proj",
"model.layers.41.self_attn.v_conv1d",
"model.layers.41.self_attn.v_proj",
"model.layers.42.hc_attn_base",
"model.layers.42.hc_attn_fn",
"model.layers.42.hc_attn_scale",
"model.layers.42.hc_ffn_base",
"model.layers.42.hc_ffn_fn",
"model.layers.42.hc_ffn_scale",
"model.layers.42.input_layernorm",
"model.layers.42.mlp.gate",
"model.layers.42.mlp.gate.e_score_correction_bias",
"model.layers.42.post_attention_layernorm",
"model.layers.42.self_attn.A_log",
"model.layers.42.self_attn.b_proj",
"model.layers.42.self_attn.dt_bias",
"model.layers.42.self_attn.f_a_proj",
"model.layers.42.self_attn.f_b_proj",
"model.layers.42.self_attn.fused_qkvbfg_a_proj",
"model.layers.42.self_attn.g_a_proj",
"model.layers.42.self_attn.g_b_proj",
"model.layers.42.self_attn.k_conv1d",
"model.layers.42.self_attn.k_proj",
"model.layers.42.self_attn.o_norm",
"model.layers.42.self_attn.o_proj",
"model.layers.42.self_attn.q_conv1d",
"model.layers.42.self_attn.q_proj",
"model.layers.42.self_attn.qkv_proj",
"model.layers.42.self_attn.v_conv1d",
"model.layers.42.self_attn.v_proj",
"model.layers.43.hc_attn_base",
"model.layers.43.hc_attn_fn",
"model.layers.43.hc_attn_scale",
"model.layers.43.hc_ffn_base",
"model.layers.43.hc_ffn_fn",
"model.layers.43.hc_ffn_scale",
"model.layers.43.input_layernorm",
"model.layers.43.mlp.gate",
"model.layers.43.mlp.gate.e_score_correction_bias",
"model.layers.43.post_attention_layernorm",
"model.layers.43.self_attn.indexer.index_kpool_compress_ape",
"model.layers.43.self_attn.indexer.index_kpool_compress_gate",
"model.layers.43.self_attn.indexer.k_norm",
"model.layers.43.self_attn.indexer.k_norm.bias",
"model.layers.43.self_attn.indexer.weights_proj",
"model.layers.43.self_attn.indexer.wk",
"model.layers.43.self_attn.indexer.wq_b",
"model.layers.43.self_attn.kv_a_layernorm",
"model.layers.43.self_attn.kv_b_proj",
"model.layers.43.self_attn.q_a_layernorm",
"model.layers.44.hc_attn_base",
"model.layers.44.hc_attn_fn",
"model.layers.44.hc_attn_scale",
"model.layers.44.hc_ffn_base",
"model.layers.44.hc_ffn_fn",
"model.layers.44.hc_ffn_scale",
"model.layers.44.input_layernorm",
"model.layers.44.mlp.gate",
"model.layers.44.mlp.gate.e_score_correction_bias",
"model.layers.44.post_attention_layernorm",
"model.layers.44.self_attn.A_log",
"model.layers.44.self_attn.b_proj",
"model.layers.44.self_attn.dt_bias",
"model.layers.44.self_attn.f_a_proj",
"model.layers.44.self_attn.f_b_proj",
"model.layers.44.self_attn.fused_qkvbfg_a_proj",
"model.layers.44.self_attn.g_a_proj",
"model.layers.44.self_attn.g_b_proj",
"model.layers.44.self_attn.k_conv1d",
"model.layers.44.self_attn.k_proj",
"model.layers.44.self_attn.o_norm",
"model.layers.44.self_attn.o_proj",
"model.layers.44.self_attn.q_conv1d",
"model.layers.44.self_attn.q_proj",
"model.layers.44.self_attn.qkv_proj",
"model.layers.44.self_attn.v_conv1d",
"model.layers.44.self_attn.v_proj",
"model.layers.45.eh_proj",
"model.layers.45.enorm",
"model.layers.45.hnorm",
"model.layers.45.input_layernorm",
"model.layers.45.mlp.gate",
"model.layers.45.mlp.gate.e_score_correction_bias",
"model.layers.45.post_attention_layernorm",
"model.layers.45.self_attn.indexer.index_kpool_compress_ape",
"model.layers.45.self_attn.indexer.index_kpool_compress_gate",
"model.layers.45.self_attn.indexer.k_norm",
"model.layers.45.self_attn.indexer.k_norm.bias",
"model.layers.45.self_attn.indexer.weights_proj",
"model.layers.45.self_attn.indexer.wk",
"model.layers.45.self_attn.indexer.wq_b",
"model.layers.45.self_attn.kv_a_layernorm",
"model.layers.45.self_attn.kv_b_proj",
"model.layers.45.self_attn.q_a_layernorm",
"model.layers.45.shared_head.norm",
"model.layers.5.hc_attn_base",
"model.layers.5.hc_attn_fn",
"model.layers.5.hc_attn_scale",
"model.layers.5.hc_ffn_base",
"model.layers.5.hc_ffn_fn",
"model.layers.5.hc_ffn_scale",
"model.layers.5.input_layernorm",
"model.layers.5.mlp.gate",
"model.layers.5.mlp.gate.e_score_correction_bias",
"model.layers.5.post_attention_layernorm",
"model.layers.5.self_attn.A_log",
"model.layers.5.self_attn.b_proj",
"model.layers.5.self_attn.dt_bias",
"model.layers.5.self_attn.f_a_proj",
"model.layers.5.self_attn.f_b_proj",
"model.layers.5.self_attn.fused_qkvbfg_a_proj",
"model.layers.5.self_attn.g_a_proj",
"model.layers.5.self_attn.g_b_proj",
"model.layers.5.self_attn.k_conv1d",
"model.layers.5.self_attn.k_proj",
"model.layers.5.self_attn.o_norm",
"model.layers.5.self_attn.o_proj",
"model.layers.5.self_attn.q_conv1d",
"model.layers.5.self_attn.q_proj",
"model.layers.5.self_attn.qkv_proj",
"model.layers.5.self_attn.v_conv1d",
"model.layers.5.self_attn.v_proj",
"model.layers.6.hc_attn_base",
"model.layers.6.hc_attn_fn",
"model.layers.6.hc_attn_scale",
"model.layers.6.hc_ffn_base",
"model.layers.6.hc_ffn_fn",
"model.layers.6.hc_ffn_scale",
"model.layers.6.input_layernorm",
"model.layers.6.mlp.gate",
"model.layers.6.mlp.gate.e_score_correction_bias",
"model.layers.6.post_attention_layernorm",
"model.layers.6.self_attn.A_log",
"model.layers.6.self_attn.b_proj",
"model.layers.6.self_attn.dt_bias",
"model.layers.6.self_attn.f_a_proj",
"model.layers.6.self_attn.f_b_proj",
"model.layers.6.self_attn.fused_qkvbfg_a_proj",
"model.layers.6.self_attn.g_a_proj",
"model.layers.6.self_attn.g_b_proj",
"model.layers.6.self_attn.k_conv1d",
"model.layers.6.self_attn.k_proj",
"model.layers.6.self_attn.o_norm",
"model.layers.6.self_attn.o_proj",
"model.layers.6.self_attn.q_conv1d",
"model.layers.6.self_attn.q_proj",
"model.layers.6.self_attn.qkv_proj",
"model.layers.6.self_attn.v_conv1d",
"model.layers.6.self_attn.v_proj",
"model.layers.7.hc_attn_base",
"model.layers.7.hc_attn_fn",
"model.layers.7.hc_attn_scale",
"model.layers.7.hc_ffn_base",
"model.layers.7.hc_ffn_fn",
"model.layers.7.hc_ffn_scale",
"model.layers.7.input_layernorm",
"model.layers.7.mlp.gate",
"model.layers.7.mlp.gate.e_score_correction_bias",
"model.layers.7.post_attention_layernorm",
"model.layers.7.self_attn.indexer.index_kpool_compress_ape",
"model.layers.7.self_attn.indexer.index_kpool_compress_gate",
"model.layers.7.self_attn.indexer.k_norm",
"model.layers.7.self_attn.indexer.k_norm.bias",
"model.layers.7.self_attn.indexer.weights_proj",
"model.layers.7.self_attn.indexer.wk",
"model.layers.7.self_attn.indexer.wq_b",
"model.layers.7.self_attn.kv_a_layernorm",
"model.layers.7.self_attn.kv_b_proj",
"model.layers.7.self_attn.q_a_layernorm",
"model.layers.8.hc_attn_base",
"model.layers.8.hc_attn_fn",
"model.layers.8.hc_attn_scale",
"model.layers.8.hc_ffn_base",
"model.layers.8.hc_ffn_fn",
"model.layers.8.hc_ffn_scale",
"model.layers.8.input_layernorm",
"model.layers.8.mlp.gate",
"model.layers.8.mlp.gate.e_score_correction_bias",
"model.layers.8.post_attention_layernorm",
"model.layers.8.self_attn.A_log",
"model.layers.8.self_attn.b_proj",
"model.layers.8.self_attn.dt_bias",
"model.layers.8.self_attn.f_a_proj",
"model.layers.8.self_attn.f_b_proj",
"model.layers.8.self_attn.fused_qkvbfg_a_proj",
"model.layers.8.self_attn.g_a_proj",
"model.layers.8.self_attn.g_b_proj",
"model.layers.8.self_attn.k_conv1d",
"model.layers.8.self_attn.k_proj",
"model.layers.8.self_attn.o_norm",
"model.layers.8.self_attn.o_proj",
"model.layers.8.self_attn.q_conv1d",
"model.layers.8.self_attn.q_proj",
"model.layers.8.self_attn.qkv_proj",
"model.layers.8.self_attn.v_conv1d",
"model.layers.8.self_attn.v_proj",
"model.layers.9.hc_attn_base",
"model.layers.9.hc_attn_fn",
"model.layers.9.hc_attn_scale",
"model.layers.9.hc_ffn_base",
"model.layers.9.hc_ffn_fn",
"model.layers.9.hc_ffn_scale",
"model.layers.9.input_layernorm",
"model.layers.9.mlp.gate",
"model.layers.9.mlp.gate.e_score_correction_bias",
"model.layers.9.post_attention_layernorm",
"model.layers.9.self_attn.A_log",
"model.layers.9.self_attn.b_proj",
"model.layers.9.self_attn.dt_bias",
"model.layers.9.self_attn.f_a_proj",
"model.layers.9.self_attn.f_b_proj",
"model.layers.9.self_attn.fused_qkvbfg_a_proj",
"model.layers.9.self_attn.g_a_proj",
"model.layers.9.self_attn.g_b_proj",
"model.layers.9.self_attn.k_conv1d",
"model.layers.9.self_attn.k_proj",
"model.layers.9.self_attn.o_norm",
"model.layers.9.self_attn.o_proj",
"model.layers.9.self_attn.q_conv1d",
"model.layers.9.self_attn.q_proj",
"model.layers.9.self_attn.qkv_proj",
"model.layers.9.self_attn.v_conv1d",
"model.layers.9.self_attn.v_proj",
"model.norm",
"model.visual",
"router",
"visual",
"visual.blocks.0.attn.k_norm",
"visual.blocks.0.attn.proj",
"visual.blocks.0.attn.proj.bias",
"visual.blocks.0.attn.q_norm",
"visual.blocks.0.attn.qkv",
"visual.blocks.0.attn.qkv.bias",
"visual.blocks.0.mlp.down_proj",
"visual.blocks.0.mlp.down_proj.bias",
"visual.blocks.0.mlp.gate_proj",
"visual.blocks.0.mlp.gate_proj.bias",
"visual.blocks.0.mlp.up_proj",
"visual.blocks.0.mlp.up_proj.bias",
"visual.blocks.0.norm1",
"visual.blocks.0.norm2",
"visual.blocks.1.attn.k_norm",
"visual.blocks.1.attn.proj",
"visual.blocks.1.attn.proj.bias",
"visual.blocks.1.attn.q_norm",
"visual.blocks.1.attn.qkv",
"visual.blocks.1.attn.qkv.bias",
"visual.blocks.1.mlp.down_proj",
"visual.blocks.1.mlp.down_proj.bias",
"visual.blocks.1.mlp.gate_proj",
"visual.blocks.1.mlp.gate_proj.bias",
"visual.blocks.1.mlp.up_proj",
"visual.blocks.1.mlp.up_proj.bias",
"visual.blocks.1.norm1",
"visual.blocks.1.norm2",
"visual.blocks.10.attn.k_norm",
"visual.blocks.10.attn.proj",
"visual.blocks.10.attn.proj.bias",
"visual.blocks.10.attn.q_norm",
"visual.blocks.10.attn.qkv",
"visual.blocks.10.attn.qkv.bias",
"visual.blocks.10.mlp.down_proj",
"visual.blocks.10.mlp.down_proj.bias",
"visual.blocks.10.mlp.gate_proj",
"visual.blocks.10.mlp.gate_proj.bias",
"visual.blocks.10.mlp.up_proj",
"visual.blocks.10.mlp.up_proj.bias",
"visual.blocks.10.norm1",
"visual.blocks.10.norm2",
"visual.blocks.11.attn.k_norm",
"visual.blocks.11.attn.proj",
"visual.blocks.11.attn.proj.bias",
"visual.blocks.11.attn.q_norm",
"visual.blocks.11.attn.qkv",
"visual.blocks.11.attn.qkv.bias",
"visual.blocks.11.mlp.down_proj",
"visual.blocks.11.mlp.down_proj.bias",
"visual.blocks.11.mlp.gate_proj",
"visual.blocks.11.mlp.gate_proj.bias",
"visual.blocks.11.mlp.up_proj",
"visual.blocks.11.mlp.up_proj.bias",
"visual.blocks.11.norm1",
"visual.blocks.11.norm2",
"visual.blocks.12.attn.k_norm",
"visual.blocks.12.attn.proj",
"visual.blocks.12.attn.proj.bias",
"visual.blocks.12.attn.q_norm",
"visual.blocks.12.attn.qkv",
"visual.blocks.12.attn.qkv.bias",
"visual.blocks.12.mlp.down_proj",
"visual.blocks.12.mlp.down_proj.bias",
"visual.blocks.12.mlp.gate_proj",
"visual.blocks.12.mlp.gate_proj.bias",
"visual.blocks.12.mlp.up_proj",
"visual.blocks.12.mlp.up_proj.bias",
"visual.blocks.12.norm1",
"visual.blocks.12.norm2",
"visual.blocks.13.attn.k_norm",
"visual.blocks.13.attn.proj",
"visual.blocks.13.attn.proj.bias",
"visual.blocks.13.attn.q_norm",
"visual.blocks.13.attn.qkv",
"visual.blocks.13.attn.qkv.bias",
"visual.blocks.13.mlp.down_proj",
"visual.blocks.13.mlp.down_proj.bias",
"visual.blocks.13.mlp.gate_proj",
"visual.blocks.13.mlp.gate_proj.bias",
"visual.blocks.13.mlp.up_proj",
"visual.blocks.13.mlp.up_proj.bias",
"visual.blocks.13.norm1",
"visual.blocks.13.norm2",
"visual.blocks.14.attn.k_norm",
"visual.blocks.14.attn.proj",
"visual.blocks.14.attn.proj.bias",
"visual.blocks.14.attn.q_norm",
"visual.blocks.14.attn.qkv",
"visual.blocks.14.attn.qkv.bias",
"visual.blocks.14.mlp.down_proj",
"visual.blocks.14.mlp.down_proj.bias",
"visual.blocks.14.mlp.gate_proj",
"visual.blocks.14.mlp.gate_proj.bias",
"visual.blocks.14.mlp.up_proj",
"visual.blocks.14.mlp.up_proj.bias",
"visual.blocks.14.norm1",
"visual.blocks.14.norm2",
"visual.blocks.15.attn.k_norm",
"visual.blocks.15.attn.proj",
"visual.blocks.15.attn.proj.bias",
"visual.blocks.15.attn.q_norm",
"visual.blocks.15.attn.qkv",
"visual.blocks.15.attn.qkv.bias",
"visual.blocks.15.mlp.down_proj",
"visual.blocks.15.mlp.down_proj.bias",
"visual.blocks.15.mlp.gate_proj",
"visual.blocks.15.mlp.gate_proj.bias",
"visual.blocks.15.mlp.up_proj",
"visual.blocks.15.mlp.up_proj.bias",
"visual.blocks.15.norm1",
"visual.blocks.15.norm2",
"visual.blocks.16.attn.k_norm",
"visual.blocks.16.attn.proj",
"visual.blocks.16.attn.proj.bias",
"visual.blocks.16.attn.q_norm",
"visual.blocks.16.attn.qkv",
"visual.blocks.16.attn.qkv.bias",
"visual.blocks.16.mlp.down_proj",
"visual.blocks.16.mlp.down_proj.bias",
"visual.blocks.16.mlp.gate_proj",
"visual.blocks.16.mlp.gate_proj.bias",
"visual.blocks.16.mlp.up_proj",
"visual.blocks.16.mlp.up_proj.bias",
"visual.blocks.16.norm1",
"visual.blocks.16.norm2",
"visual.blocks.17.attn.k_norm",
"visual.blocks.17.attn.proj",
"visual.blocks.17.attn.proj.bias",
"visual.blocks.17.attn.q_norm",
"visual.blocks.17.attn.qkv",
"visual.blocks.17.attn.qkv.bias",
"visual.blocks.17.mlp.down_proj",
"visual.blocks.17.mlp.down_proj.bias",
"visual.blocks.17.mlp.gate_proj",
"visual.blocks.17.mlp.gate_proj.bias",
"visual.blocks.17.mlp.up_proj",
"visual.blocks.17.mlp.up_proj.bias",
"visual.blocks.17.norm1",
"visual.blocks.17.norm2",
"visual.blocks.18.attn.k_norm",
"visual.blocks.18.attn.proj",
"visual.blocks.18.attn.proj.bias",
"visual.blocks.18.attn.q_norm",
"visual.blocks.18.attn.qkv",
"visual.blocks.18.attn.qkv.bias",
"visual.blocks.18.mlp.down_proj",
"visual.blocks.18.mlp.down_proj.bias",
"visual.blocks.18.mlp.gate_proj",
"visual.blocks.18.mlp.gate_proj.bias",
"visual.blocks.18.mlp.up_proj",
"visual.blocks.18.mlp.up_proj.bias",
"visual.blocks.18.norm1",
"visual.blocks.18.norm2",
"visual.blocks.19.attn.k_norm",
"visual.blocks.19.attn.proj",
"visual.blocks.19.attn.proj.bias",
"visual.blocks.19.attn.q_norm",
"visual.blocks.19.attn.qkv",
"visual.blocks.19.attn.qkv.bias",
"visual.blocks.19.mlp.down_proj",
"visual.blocks.19.mlp.down_proj.bias",
"visual.blocks.19.mlp.gate_proj",
"visual.blocks.19.mlp.gate_proj.bias",
"visual.blocks.19.mlp.up_proj",
"visual.blocks.19.mlp.up_proj.bias",
"visual.blocks.19.norm1",
"visual.blocks.19.norm2",
"visual.blocks.2.attn.k_norm",
"visual.blocks.2.attn.proj",
"visual.blocks.2.attn.proj.bias",
"visual.blocks.2.attn.q_norm",
"visual.blocks.2.attn.qkv",
"visual.blocks.2.attn.qkv.bias",
"visual.blocks.2.mlp.down_proj",
"visual.blocks.2.mlp.down_proj.bias",
"visual.blocks.2.mlp.gate_proj",
"visual.blocks.2.mlp.gate_proj.bias",
"visual.blocks.2.mlp.up_proj",
"visual.blocks.2.mlp.up_proj.bias",
"visual.blocks.2.norm1",
"visual.blocks.2.norm2",
"visual.blocks.20.attn.k_norm",
"visual.blocks.20.attn.proj",
"visual.blocks.20.attn.proj.bias",
"visual.blocks.20.attn.q_norm",
"visual.blocks.20.attn.qkv",
"visual.blocks.20.attn.qkv.bias",
"visual.blocks.20.mlp.down_proj",
"visual.blocks.20.mlp.down_proj.bias",
"visual.blocks.20.mlp.gate_proj",
"visual.blocks.20.mlp.gate_proj.bias",
"visual.blocks.20.mlp.up_proj",
"visual.blocks.20.mlp.up_proj.bias",
"visual.blocks.20.norm1",
"visual.blocks.20.norm2",
"visual.blocks.21.attn.k_norm",
"visual.blocks.21.attn.proj",
"visual.blocks.21.attn.proj.bias",
"visual.blocks.21.attn.q_norm",
"visual.blocks.21.attn.qkv",
"visual.blocks.21.attn.qkv.bias",
"visual.blocks.21.mlp.down_proj",
"visual.blocks.21.mlp.down_proj.bias",
"visual.blocks.21.mlp.gate_proj",
"visual.blocks.21.mlp.gate_proj.bias",
"visual.blocks.21.mlp.up_proj",
"visual.blocks.21.mlp.up_proj.bias",
"visual.blocks.21.norm1",
"visual.blocks.21.norm2",
"visual.blocks.22.attn.k_norm",
"visual.blocks.22.attn.proj",
"visual.blocks.22.attn.proj.bias",
"visual.blocks.22.attn.q_norm",
"visual.blocks.22.attn.qkv",
"visual.blocks.22.attn.qkv.bias",
"visual.blocks.22.mlp.down_proj",
"visual.blocks.22.mlp.down_proj.bias",
"visual.blocks.22.mlp.gate_proj",
"visual.blocks.22.mlp.gate_proj.bias",
"visual.blocks.22.mlp.up_proj",
"visual.blocks.22.mlp.up_proj.bias",
"visual.blocks.22.norm1",
"visual.blocks.22.norm2",
"visual.blocks.23.attn.k_norm",
"visual.blocks.23.attn.proj",
"visual.blocks.23.attn.proj.bias",
"visual.blocks.23.attn.q_norm",
"visual.blocks.23.attn.qkv",
"visual.blocks.23.attn.qkv.bias",
"visual.blocks.23.mlp.down_proj",
"visual.blocks.23.mlp.down_proj.bias",
"visual.blocks.23.mlp.gate_proj",
"visual.blocks.23.mlp.gate_proj.bias",
"visual.blocks.23.mlp.up_proj",
"visual.blocks.23.mlp.up_proj.bias",
"visual.blocks.23.norm1",
"visual.blocks.23.norm2",
"visual.blocks.3.attn.k_norm",
"visual.blocks.3.attn.proj",
"visual.blocks.3.attn.proj.bias",
"visual.blocks.3.attn.q_norm",
"visual.blocks.3.attn.qkv",
"visual.blocks.3.attn.qkv.bias",
"visual.blocks.3.mlp.down_proj",
"visual.blocks.3.mlp.down_proj.bias",
"visual.blocks.3.mlp.gate_proj",
"visual.blocks.3.mlp.gate_proj.bias",
"visual.blocks.3.mlp.up_proj",
"visual.blocks.3.mlp.up_proj.bias",
"visual.blocks.3.norm1",
"visual.blocks.3.norm2",
"visual.blocks.4.attn.k_norm",
"visual.blocks.4.attn.proj",
"visual.blocks.4.attn.proj.bias",
"visual.blocks.4.attn.q_norm",
"visual.blocks.4.attn.qkv",
"visual.blocks.4.attn.qkv.bias",
"visual.blocks.4.mlp.down_proj",
"visual.blocks.4.mlp.down_proj.bias",
"visual.blocks.4.mlp.gate_proj",
"visual.blocks.4.mlp.gate_proj.bias",
"visual.blocks.4.mlp.up_proj",
"visual.blocks.4.mlp.up_proj.bias",
"visual.blocks.4.norm1",
"visual.blocks.4.norm2",
"visual.blocks.5.attn.k_norm",
"visual.blocks.5.attn.proj",
"visual.blocks.5.attn.proj.bias",
"visual.blocks.5.attn.q_norm",
"visual.blocks.5.attn.qkv",
"visual.blocks.5.attn.qkv.bias",
"visual.blocks.5.mlp.down_proj",
"visual.blocks.5.mlp.down_proj.bias",
"visual.blocks.5.mlp.gate_proj",
"visual.blocks.5.mlp.gate_proj.bias",
"visual.blocks.5.mlp.up_proj",
"visual.blocks.5.mlp.up_proj.bias",
"visual.blocks.5.norm1",
"visual.blocks.5.norm2",
"visual.blocks.6.attn.k_norm",
"visual.blocks.6.attn.proj",
"visual.blocks.6.attn.proj.bias",
"visual.blocks.6.attn.q_norm",
"visual.blocks.6.attn.qkv",
"visual.blocks.6.attn.qkv.bias",
"visual.blocks.6.mlp.down_proj",
"visual.blocks.6.mlp.down_proj.bias",
"visual.blocks.6.mlp.gate_proj",
"visual.blocks.6.mlp.gate_proj.bias",
"visual.blocks.6.mlp.up_proj",
"visual.blocks.6.mlp.up_proj.bias",
"visual.blocks.6.norm1",
"visual.blocks.6.norm2",
"visual.blocks.7.attn.k_norm",
"visual.blocks.7.attn.proj",
"visual.blocks.7.attn.proj.bias",
"visual.blocks.7.attn.q_norm",
"visual.blocks.7.attn.qkv",
"visual.blocks.7.attn.qkv.bias",
"visual.blocks.7.mlp.down_proj",
"visual.blocks.7.mlp.down_proj.bias",
"visual.blocks.7.mlp.gate_proj",
"visual.blocks.7.mlp.gate_proj.bias",
"visual.blocks.7.mlp.up_proj",
"visual.blocks.7.mlp.up_proj.bias",
"visual.blocks.7.norm1",
"visual.blocks.7.norm2",
"visual.blocks.8.attn.k_norm",
"visual.blocks.8.attn.proj",
"visual.blocks.8.attn.proj.bias",
"visual.blocks.8.attn.q_norm",
"visual.blocks.8.attn.qkv",
"visual.blocks.8.attn.qkv.bias",
"visual.blocks.8.mlp.down_proj",
"visual.blocks.8.mlp.down_proj.bias",
"visual.blocks.8.mlp.gate_proj",
"visual.blocks.8.mlp.gate_proj.bias",
"visual.blocks.8.mlp.up_proj",
"visual.blocks.8.mlp.up_proj.bias",
"visual.blocks.8.norm1",
"visual.blocks.8.norm2",
"visual.blocks.9.attn.k_norm",
"visual.blocks.9.attn.proj",
"visual.blocks.9.attn.proj.bias",
"visual.blocks.9.attn.q_norm",
"visual.blocks.9.attn.qkv",
"visual.blocks.9.attn.qkv.bias",
"visual.blocks.9.mlp.down_proj",
"visual.blocks.9.mlp.down_proj.bias",
"visual.blocks.9.mlp.gate_proj",
"visual.blocks.9.mlp.gate_proj.bias",
"visual.blocks.9.mlp.up_proj",
"visual.blocks.9.mlp.up_proj.bias",
"visual.blocks.9.norm1",
"visual.blocks.9.norm2",
"visual.downsample",
"visual.downsample.bias",
"visual.merger.down_proj",
"visual.merger.gate_proj",
"visual.merger.post_projection_norm",
"visual.merger.post_projection_norm.bias",
"visual.merger.proj",
"visual.merger.up_proj",
"visual.patch_embed.proj",
"visual.patch_embed.proj.bias",
"visual.post_layernorm",
"weights_proj"
],
"quant_method": "fp8"
},
"tokenizer_config": {
"eos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>"
}
},
"createdAt": "2026-08-26T21:09:20.000Z",
"disabled": false,
"downloads": 49224,
"gated": false,
"id": "dealignai/GLM-5.3-Flash-UNCENSORED-FP8",
"lastModified": "2026-09-19T16:32:29.000Z",
"likes": 126,
"model-index": null,
"modelId": "dealignai/GLM-5.3-Flash-UNCENSORED-FP8",
"private": false,
"safetensors": {
"parameters": {
"BF16": 6926096640,
"F32": 295518,
"F8_E4M3": 314396639232
},
"total": 321323031390
},
"sha": "d5822b068da8ddb301665b48c58718e6e18a2c3a",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "dealign_logo.png"
},
{
"rfilename": "dealign_mascot.png"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "model-00001-of-00062.safetensors"
},
{
"rfilename": "model-00002-of-00062.safetensors"
},
{
"rfilename": "model-00003-of-00062.safetensors"
},
{
"rfilename": "model-00004-of-00062.safetensors"
},
{
"rfilename": "model-00005-of-00062.safetensors"
},
{
"rfilename": "model-00006-of-00062.safetensors"
},
{
"rfilename": "model-00007-of-00062.safetensors"
},
{
"rfilename": "model-00008-of-00062.safetensors"
},
{
"rfilename": "model-00009-of-00062.safetensors"
},
{
"rfilename": "model-00010-of-00062.safetensors"
},
{
"rfilename": "model-00011-of-00062.safetensors"
},
{
"rfilename": "model-00012-of-00062.safetensors"
},
{
"rfilename": "model-00013-of-00062.safetensors"
},
{
"rfilename": "model-00014-of-00062.safetensors"
},
{
"rfilename": "model-00015-of-00062.safetensors"
},
{
"rfilename": "model-00016-of-00062.safetensors"
},
{
"rfilename": "model-00017-of-00062.safetensors"
},
{
"rfilename": "model-00018-of-00062.safetensors"
},
{
"rfilename": "model-00019-of-00062.safetensors"
},
{
"rfilename": "model-00020-of-00062.safetensors"
},
{
"rfilename": "model-00021-of-00062.safetensors"
},
{
"rfilename": "model-00022-of-00062.safetensors"
},
{
"rfilename": "model-00023-of-00062.safetensors"
},
{
"rfilename": "model-00024-of-00062.safetensors"
},
{
"rfilename": "model-00025-of-00062.safetensors"
},
{
"rfilename": "model-00026-of-00062.safetensors"
},
{
"rfilename": "model-00027-of-00062.safetensors"
},
{
"rfilename": "model-00028-of-00062.safetensors"
},
{
"rfilename": "model-00029-of-00062.safetensors"
},
{
"rfilename": "model-00030-of-00062.safetensors"
},
{
"rfilename": "model-00031-of-00062.safetensors"
},
{
"rfilename": "model-00032-of-00062.safetensors"
},
{
"rfilename": "model-00033-of-00062.safetensors"
},
{
"rfilename": "model-00034-of-00062.safetensors"
},
{
"rfilename": "model-00035-of-00062.safetensors"
},
{
"rfilename": "model-00036-of-00062.safetensors"
},
{
"rfilename": "model-00037-of-00062.safetensors"
},
{
"rfilename": "model-00038-of-00062.safetensors"
},
{
"rfilename": "model-00039-of-00062.safetensors"
},
{
"rfilename": "model-00040-of-00062.safetensors"
},
{
"rfilename": "model-00041-of-00062.safetensors"
},
{
"rfilename": "model-00042-of-00062.safetensors"
},
{
"rfilename": "model-00043-of-00062.safetensors"
},
{
"rfilename": "model-00044-of-00062.safetensors"
},
{
"rfilename": "model-00045-of-00062.safetensors"
},
{
"rfilename": "model-00046-of-00062.safetensors"
},
{
"rfilename": "model-00047-of-00062.safetensors"
},
{
"rfilename": "model-00048-of-00062.safetensors"
},
{
"rfilename": "model-00049-of-00062.safetensors"
},
{
"rfilename": "model-00050-of-00062.safetensors"
},
{
"rfilename": "model-00051-of-00062.safetensors"
},
{
"rfilename": "model-00052-of-00062.safetensors"
},
{
"rfilename": "model-00053-of-00062.safetensors"
},
{
"rfilename": "model-00054-of-00062.safetensors"
},
{
"rfilename": "model-00055-of-00062.safetensors"
},
{
"rfilename": "model-00056-of-00062.safetensors"
},
{
"rfilename": "model-00057-of-00062.safetensors"
},
{
"rfilename": "model-00058-of-00062.safetensors"
},
{
"rfilename": "model-00059-of-00062.safetensors"
},
{
"rfilename": "model-00060-of-00062.safetensors"
},
{
"rfilename": "model-00061-of-00062.safetensors"
},
{
"rfilename": "model-00062-of-00062.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "processor_config.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
}
],
"spaces": [
"tardellirs/model-pulse",
"aquanode/gpu-vram-calculator"
],
"tags": [
"safetensors",
"glm5_next",
"abliterated",
"uncensored",
"crack",
"glm",
"moe",
"fp8",
"vision",
"mtp",
"en",
"base_model:zai-org/GLM-5.3-Flash",
"base_model:quantized:zai-org/GLM-5.3-Flash",
"license:mit",
"region:us"
],
"usedStorage": 505375369250
} |
Text
This source's terms allow its title, its values and a link here, not its text. It is at https://huggingface.co/dealignai/GLM-5.3-Flash-UNCENSORED-FP8.