deepseek-ai/DeepSeek-V2-Lite
zetlyn/models-hf model hf deepseek-ai/DeepSeek-V2-Lite known 2024-05-15
https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite
Properties
| author | deepseek-aireceipt
What the source handed over{
"_asked": "deepseek-ai/DeepSeek-V2-Lite",
"_id": "664448c9ba3c6c8d118eb0e7",
"author": "deepseek-ai",
"cardData": {
"license": "other",
"license_link": "https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL",
"license_name": "deepseek"
},
"config": {
"architectures": [
"DeepseekV2ForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_deepseek.DeepseekV2Config",
"AutoModel": "modeling_deepseek.DeepseekV2Model",
"AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
},
"model_type": "deepseek_v2",
"num_experts_per_tok": 6,
"tokenizer_config": {
"bos_token": {
"__type": "AddedToken",
"content": "<|begin▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
"eos_token": {
"__type": "AddedToken",
"content": "<|end▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": {
"__type": "AddedToken",
"content": "<|end▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unk_token": null
}
},
"createdAt": "2024-05-15T05:31:53.000Z",
"disabled": false,
"downloads": 216842,
"gated": false,
"id": "deepseek-ai/DeepSeek-V2-Lite",
"lastModified": "2024-06-25T08:37:17.000Z",
"library_name": "transformers",
"likes": 190,
"model-index": null,
"modelId": "deepseek-ai/DeepSeek-V2-Lite",
"pipeline_tag": "text-generation",
"private": false,
"safetensors": {
"parameters": {
"BF16": 15706484224
},
"total": 15706484224
},
"sha": "604d5664dddd88a0433dbae533b7fe9472482de0",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "config.json"
},
{
"rfilename": "configuration_deepseek.py"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "model-00001-of-000004.safetensors"
},
{
"rfilename": "model-00002-of-000004.safetensors"
},
{
"rfilename": "model-00003-of-000004.safetensors"
},
{
"rfilename": "model-00004-of-000004.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "modeling_deepseek.py"
},
{
"rfilename": "tokenization_deepseek_fast.py"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
}
],
"spaces": [
"embedl/hfviewer",
"tardellirs/model-pulse",
"aquanode/gpu-vram-calculator",
"eduagarcia/open_pt_llm_leaderboard",
"ginigen-ai/Metacognition-Leaderboard-Space",
"Justinrune/LLaMA-Factory",
"Livengood/Instance-VRAM-Calculator",
"mlanvvs/fitcheck",
"dhlak/llm-vram-calc",
"luancy1208/CHIP",
"aekpic877/MathAI",
"msun415/Llamole",
"Hachiru/chigas",
"terr97us/my-deepseek-demo",
"MAS-AI-0000/Authentica",
"Unique023/Darshan_s_Pizza_House",
"MedusaDiaspora/Burger-Concierge",
"hplisiecki/pinocchio-inventory-explorer",
"zst50/MoE-Parameter-Calculator"
],
"tags": [
"transformers",
"safetensors",
"deepseek_v2",
"text-generation",
"conversational",
"custom_code",
"arxiv:2405.04434",
"license:other",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForCausalLM",
"pipeline_tag": "text-generation",
"processor": "AutoTokenizer"
},
"usedStorage": 31413626576,
"widgetData": [
{
"text": "Hi, what can you help me with?"
},
{
"text": "What is 84 * 3 / 2?"
},
{
"text": "Tell me an interesting fact about the universe!"
},
{
"text": "Explain quantum computing in simple terms."
}
]
} | ||||||
|---|---|---|---|---|---|---|---|
| downloads | 216842receipt
What the source handed over{
"_asked": "deepseek-ai/DeepSeek-V2-Lite",
"_id": "664448c9ba3c6c8d118eb0e7",
"author": "deepseek-ai",
"cardData": {
"license": "other",
"license_link": "https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL",
"license_name": "deepseek"
},
"config": {
"architectures": [
"DeepseekV2ForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_deepseek.DeepseekV2Config",
"AutoModel": "modeling_deepseek.DeepseekV2Model",
"AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
},
"model_type": "deepseek_v2",
"num_experts_per_tok": 6,
"tokenizer_config": {
"bos_token": {
"__type": "AddedToken",
"content": "<|begin▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
"eos_token": {
"__type": "AddedToken",
"content": "<|end▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": {
"__type": "AddedToken",
"content": "<|end▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unk_token": null
}
},
"createdAt": "2024-05-15T05:31:53.000Z",
"disabled": false,
"downloads": 216842,
"gated": false,
"id": "deepseek-ai/DeepSeek-V2-Lite",
"lastModified": "2024-06-25T08:37:17.000Z",
"library_name": "transformers",
"likes": 190,
"model-index": null,
"modelId": "deepseek-ai/DeepSeek-V2-Lite",
"pipeline_tag": "text-generation",
"private": false,
"safetensors": {
"parameters": {
"BF16": 15706484224
},
"total": 15706484224
},
"sha": "604d5664dddd88a0433dbae533b7fe9472482de0",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "config.json"
},
{
"rfilename": "configuration_deepseek.py"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "model-00001-of-000004.safetensors"
},
{
"rfilename": "model-00002-of-000004.safetensors"
},
{
"rfilename": "model-00003-of-000004.safetensors"
},
{
"rfilename": "model-00004-of-000004.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "modeling_deepseek.py"
},
{
"rfilename": "tokenization_deepseek_fast.py"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
}
],
"spaces": [
"embedl/hfviewer",
"tardellirs/model-pulse",
"aquanode/gpu-vram-calculator",
"eduagarcia/open_pt_llm_leaderboard",
"ginigen-ai/Metacognition-Leaderboard-Space",
"Justinrune/LLaMA-Factory",
"Livengood/Instance-VRAM-Calculator",
"mlanvvs/fitcheck",
"dhlak/llm-vram-calc",
"luancy1208/CHIP",
"aekpic877/MathAI",
"msun415/Llamole",
"Hachiru/chigas",
"terr97us/my-deepseek-demo",
"MAS-AI-0000/Authentica",
"Unique023/Darshan_s_Pizza_House",
"MedusaDiaspora/Burger-Concierge",
"hplisiecki/pinocchio-inventory-explorer",
"zst50/MoE-Parameter-Calculator"
],
"tags": [
"transformers",
"safetensors",
"deepseek_v2",
"text-generation",
"conversational",
"custom_code",
"arxiv:2405.04434",
"license:other",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForCausalLM",
"pipeline_tag": "text-generation",
"processor": "AutoTokenizer"
},
"usedStorage": 31413626576,
"widgetData": [
{
"text": "Hi, what can you help me with?"
},
{
"text": "What is 84 * 3 / 2?"
},
{
"text": "Tell me an interesting fact about the universe!"
},
{
"text": "Explain quantum computing in simple terms."
}
]
} | ||||||
| gated | falsereceipt
What the source handed over{
"_asked": "deepseek-ai/DeepSeek-V2-Lite",
"_id": "664448c9ba3c6c8d118eb0e7",
"author": "deepseek-ai",
"cardData": {
"license": "other",
"license_link": "https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL",
"license_name": "deepseek"
},
"config": {
"architectures": [
"DeepseekV2ForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_deepseek.DeepseekV2Config",
"AutoModel": "modeling_deepseek.DeepseekV2Model",
"AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
},
"model_type": "deepseek_v2",
"num_experts_per_tok": 6,
"tokenizer_config": {
"bos_token": {
"__type": "AddedToken",
"content": "<|begin▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
"eos_token": {
"__type": "AddedToken",
"content": "<|end▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": {
"__type": "AddedToken",
"content": "<|end▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unk_token": null
}
},
"createdAt": "2024-05-15T05:31:53.000Z",
"disabled": false,
"downloads": 216842,
"gated": false,
"id": "deepseek-ai/DeepSeek-V2-Lite",
"lastModified": "2024-06-25T08:37:17.000Z",
"library_name": "transformers",
"likes": 190,
"model-index": null,
"modelId": "deepseek-ai/DeepSeek-V2-Lite",
"pipeline_tag": "text-generation",
"private": false,
"safetensors": {
"parameters": {
"BF16": 15706484224
},
"total": 15706484224
},
"sha": "604d5664dddd88a0433dbae533b7fe9472482de0",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "config.json"
},
{
"rfilename": "configuration_deepseek.py"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "model-00001-of-000004.safetensors"
},
{
"rfilename": "model-00002-of-000004.safetensors"
},
{
"rfilename": "model-00003-of-000004.safetensors"
},
{
"rfilename": "model-00004-of-000004.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "modeling_deepseek.py"
},
{
"rfilename": "tokenization_deepseek_fast.py"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
}
],
"spaces": [
"embedl/hfviewer",
"tardellirs/model-pulse",
"aquanode/gpu-vram-calculator",
"eduagarcia/open_pt_llm_leaderboard",
"ginigen-ai/Metacognition-Leaderboard-Space",
"Justinrune/LLaMA-Factory",
"Livengood/Instance-VRAM-Calculator",
"mlanvvs/fitcheck",
"dhlak/llm-vram-calc",
"luancy1208/CHIP",
"aekpic877/MathAI",
"msun415/Llamole",
"Hachiru/chigas",
"terr97us/my-deepseek-demo",
"MAS-AI-0000/Authentica",
"Unique023/Darshan_s_Pizza_House",
"MedusaDiaspora/Burger-Concierge",
"hplisiecki/pinocchio-inventory-explorer",
"zst50/MoE-Parameter-Calculator"
],
"tags": [
"transformers",
"safetensors",
"deepseek_v2",
"text-generation",
"conversational",
"custom_code",
"arxiv:2405.04434",
"license:other",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForCausalLM",
"pipeline_tag": "text-generation",
"processor": "AutoTokenizer"
},
"usedStorage": 31413626576,
"widgetData": [
{
"text": "Hi, what can you help me with?"
},
{
"text": "What is 84 * 3 / 2?"
},
{
"text": "Tell me an interesting fact about the universe!"
},
{
"text": "Explain quantum computing in simple terms."
}
]
} | ||||||
| licence | otherreceipt
What the source handed over{
"_asked": "deepseek-ai/DeepSeek-V2-Lite",
"_id": "664448c9ba3c6c8d118eb0e7",
"author": "deepseek-ai",
"cardData": {
"license": "other",
"license_link": "https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL",
"license_name": "deepseek"
},
"config": {
"architectures": [
"DeepseekV2ForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_deepseek.DeepseekV2Config",
"AutoModel": "modeling_deepseek.DeepseekV2Model",
"AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
},
"model_type": "deepseek_v2",
"num_experts_per_tok": 6,
"tokenizer_config": {
"bos_token": {
"__type": "AddedToken",
"content": "<|begin▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
"eos_token": {
"__type": "AddedToken",
"content": "<|end▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": {
"__type": "AddedToken",
"content": "<|end▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unk_token": null
}
},
"createdAt": "2024-05-15T05:31:53.000Z",
"disabled": false,
"downloads": 216842,
"gated": false,
"id": "deepseek-ai/DeepSeek-V2-Lite",
"lastModified": "2024-06-25T08:37:17.000Z",
"library_name": "transformers",
"likes": 190,
"model-index": null,
"modelId": "deepseek-ai/DeepSeek-V2-Lite",
"pipeline_tag": "text-generation",
"private": false,
"safetensors": {
"parameters": {
"BF16": 15706484224
},
"total": 15706484224
},
"sha": "604d5664dddd88a0433dbae533b7fe9472482de0",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "config.json"
},
{
"rfilename": "configuration_deepseek.py"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "model-00001-of-000004.safetensors"
},
{
"rfilename": "model-00002-of-000004.safetensors"
},
{
"rfilename": "model-00003-of-000004.safetensors"
},
{
"rfilename": "model-00004-of-000004.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "modeling_deepseek.py"
},
{
"rfilename": "tokenization_deepseek_fast.py"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
}
],
"spaces": [
"embedl/hfviewer",
"tardellirs/model-pulse",
"aquanode/gpu-vram-calculator",
"eduagarcia/open_pt_llm_leaderboard",
"ginigen-ai/Metacognition-Leaderboard-Space",
"Justinrune/LLaMA-Factory",
"Livengood/Instance-VRAM-Calculator",
"mlanvvs/fitcheck",
"dhlak/llm-vram-calc",
"luancy1208/CHIP",
"aekpic877/MathAI",
"msun415/Llamole",
"Hachiru/chigas",
"terr97us/my-deepseek-demo",
"MAS-AI-0000/Authentica",
"Unique023/Darshan_s_Pizza_House",
"MedusaDiaspora/Burger-Concierge",
"hplisiecki/pinocchio-inventory-explorer",
"zst50/MoE-Parameter-Calculator"
],
"tags": [
"transformers",
"safetensors",
"deepseek_v2",
"text-generation",
"conversational",
"custom_code",
"arxiv:2405.04434",
"license:other",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForCausalLM",
"pipeline_tag": "text-generation",
"processor": "AutoTokenizer"
},
"usedStorage": 31413626576,
"widgetData": [
{
"text": "Hi, what can you help me with?"
},
{
"text": "What is 84 * 3 / 2?"
},
{
"text": "Tell me an interesting fact about the universe!"
},
{
"text": "Explain quantum computing in simple terms."
}
]
} | ||||||
| likes | 190receipt
What the source handed over{
"_asked": "deepseek-ai/DeepSeek-V2-Lite",
"_id": "664448c9ba3c6c8d118eb0e7",
"author": "deepseek-ai",
"cardData": {
"license": "other",
"license_link": "https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL",
"license_name": "deepseek"
},
"config": {
"architectures": [
"DeepseekV2ForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_deepseek.DeepseekV2Config",
"AutoModel": "modeling_deepseek.DeepseekV2Model",
"AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
},
"model_type": "deepseek_v2",
"num_experts_per_tok": 6,
"tokenizer_config": {
"bos_token": {
"__type": "AddedToken",
"content": "<|begin▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
"eos_token": {
"__type": "AddedToken",
"content": "<|end▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": {
"__type": "AddedToken",
"content": "<|end▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unk_token": null
}
},
"createdAt": "2024-05-15T05:31:53.000Z",
"disabled": false,
"downloads": 216842,
"gated": false,
"id": "deepseek-ai/DeepSeek-V2-Lite",
"lastModified": "2024-06-25T08:37:17.000Z",
"library_name": "transformers",
"likes": 190,
"model-index": null,
"modelId": "deepseek-ai/DeepSeek-V2-Lite",
"pipeline_tag": "text-generation",
"private": false,
"safetensors": {
"parameters": {
"BF16": 15706484224
},
"total": 15706484224
},
"sha": "604d5664dddd88a0433dbae533b7fe9472482de0",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "config.json"
},
{
"rfilename": "configuration_deepseek.py"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "model-00001-of-000004.safetensors"
},
{
"rfilename": "model-00002-of-000004.safetensors"
},
{
"rfilename": "model-00003-of-000004.safetensors"
},
{
"rfilename": "model-00004-of-000004.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "modeling_deepseek.py"
},
{
"rfilename": "tokenization_deepseek_fast.py"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
}
],
"spaces": [
"embedl/hfviewer",
"tardellirs/model-pulse",
"aquanode/gpu-vram-calculator",
"eduagarcia/open_pt_llm_leaderboard",
"ginigen-ai/Metacognition-Leaderboard-Space",
"Justinrune/LLaMA-Factory",
"Livengood/Instance-VRAM-Calculator",
"mlanvvs/fitcheck",
"dhlak/llm-vram-calc",
"luancy1208/CHIP",
"aekpic877/MathAI",
"msun415/Llamole",
"Hachiru/chigas",
"terr97us/my-deepseek-demo",
"MAS-AI-0000/Authentica",
"Unique023/Darshan_s_Pizza_House",
"MedusaDiaspora/Burger-Concierge",
"hplisiecki/pinocchio-inventory-explorer",
"zst50/MoE-Parameter-Calculator"
],
"tags": [
"transformers",
"safetensors",
"deepseek_v2",
"text-generation",
"conversational",
"custom_code",
"arxiv:2405.04434",
"license:other",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForCausalLM",
"pipeline_tag": "text-generation",
"processor": "AutoTokenizer"
},
"usedStorage": 31413626576,
"widgetData": [
{
"text": "Hi, what can you help me with?"
},
{
"text": "What is 84 * 3 / 2?"
},
{
"text": "Tell me an interesting fact about the universe!"
},
{
"text": "Explain quantum computing in simple terms."
}
]
} | ||||||
| task | text-generationreceipt
What the source handed over{
"_asked": "deepseek-ai/DeepSeek-V2-Lite",
"_id": "664448c9ba3c6c8d118eb0e7",
"author": "deepseek-ai",
"cardData": {
"license": "other",
"license_link": "https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL",
"license_name": "deepseek"
},
"config": {
"architectures": [
"DeepseekV2ForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_deepseek.DeepseekV2Config",
"AutoModel": "modeling_deepseek.DeepseekV2Model",
"AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
},
"model_type": "deepseek_v2",
"num_experts_per_tok": 6,
"tokenizer_config": {
"bos_token": {
"__type": "AddedToken",
"content": "<|begin▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
"eos_token": {
"__type": "AddedToken",
"content": "<|end▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": {
"__type": "AddedToken",
"content": "<|end▁of▁sentence|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unk_token": null
}
},
"createdAt": "2024-05-15T05:31:53.000Z",
"disabled": false,
"downloads": 216842,
"gated": false,
"id": "deepseek-ai/DeepSeek-V2-Lite",
"lastModified": "2024-06-25T08:37:17.000Z",
"library_name": "transformers",
"likes": 190,
"model-index": null,
"modelId": "deepseek-ai/DeepSeek-V2-Lite",
"pipeline_tag": "text-generation",
"private": false,
"safetensors": {
"parameters": {
"BF16": 15706484224
},
"total": 15706484224
},
"sha": "604d5664dddd88a0433dbae533b7fe9472482de0",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "README.md"
},
{
"rfilename": "config.json"
},
{
"rfilename": "configuration_deepseek.py"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "model-00001-of-000004.safetensors"
},
{
"rfilename": "model-00002-of-000004.safetensors"
},
{
"rfilename": "model-00003-of-000004.safetensors"
},
{
"rfilename": "model-00004-of-000004.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "modeling_deepseek.py"
},
{
"rfilename": "tokenization_deepseek_fast.py"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
}
],
"spaces": [
"embedl/hfviewer",
"tardellirs/model-pulse",
"aquanode/gpu-vram-calculator",
"eduagarcia/open_pt_llm_leaderboard",
"ginigen-ai/Metacognition-Leaderboard-Space",
"Justinrune/LLaMA-Factory",
"Livengood/Instance-VRAM-Calculator",
"mlanvvs/fitcheck",
"dhlak/llm-vram-calc",
"luancy1208/CHIP",
"aekpic877/MathAI",
"msun415/Llamole",
"Hachiru/chigas",
"terr97us/my-deepseek-demo",
"MAS-AI-0000/Authentica",
"Unique023/Darshan_s_Pizza_House",
"MedusaDiaspora/Burger-Concierge",
"hplisiecki/pinocchio-inventory-explorer",
"zst50/MoE-Parameter-Calculator"
],
"tags": [
"transformers",
"safetensors",
"deepseek_v2",
"text-generation",
"conversational",
"custom_code",
"arxiv:2405.04434",
"license:other",
"text-generation-inference",
"endpoints_compatible",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForCausalLM",
"pipeline_tag": "text-generation",
"processor": "AutoTokenizer"
},
"usedStorage": 31413626576,
"widgetData": [
{
"text": "Hi, what can you help me with?"
},
{
"text": "What is 84 * 3 / 2?"
},
{
"text": "Tell me an interesting fact about the universe!"
},
{
"text": "Explain quantum computing in simple terms."
}
]
} |
Text
This source's terms allow its title, its values and a link here, not its text. It is at https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite.