Dharma-AI/Dharma-OCR-LITE
zetlyn/models-hf model hf Dharma-AI/Dharma-OCR-LITE known 2026-03-29
https://huggingface.co/Dharma-AI/Dharma-OCR-LITE
Properties
| author | Dharma-AIreceipt
What the source handed over{
"_asked": "Dharma-AI/Dharma-OCR-LITE",
"_id": "69c875c8fc5631a422c50143",
"author": "Dharma-AI",
"cardData": {
"datasets": [
"dharma-ai/DharmaOCR-Benchmark"
],
"language": [
"pt"
],
"library_name": "transformers",
"license": "other",
"license_link": "LICENSE",
"license_name": "dharmaocr-lite-license",
"pipeline_tag": "image-text-to-text",
"tags": [
"ocr",
"document-understanding",
"structured-extraction",
"specialized-small-language-model",
"brazilian-portuguese"
]
},
"config": {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"chat_template_jinja": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or (('image' in content or 'image_url' in content) and content['type'] != 'text') %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
"model_type": "qwen2_5_vl",
"quantization_config": {
"config_groups": {
"group_0": {
"format": "float-quantized",
"targets": [
"Linear"
],
"weights": {
"num_bits": 8
}
}
},
"format": "float-quantized",
"quant_method": "compressed-tensors"
},
"tokenizer_config": {
"bos_token": null,
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2026-03-29T00:43:52.000Z",
"disabled": false,
"downloads": 370,
"gated": false,
"id": "Dharma-AI/Dharma-OCR-LITE",
"lastModified": "2026-04-17T12:10:30.000Z",
"library_name": "transformers",
"likes": 22,
"model-index": null,
"modelId": "Dharma-AI/Dharma-OCR-LITE",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"BF16": 1291256312,
"F8_E4M3": 2774532096
},
"total": 4065788408
},
"sha": "3fd38b0c131fffc7c812e70bab626a317d96ef57",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "NOTICE.txt"
},
{
"rfilename": "README.md"
},
{
"rfilename": "added_tokens.json"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "images/cost_x_score.png"
},
{
"rfilename": "images/example_text_degeneration.png"
},
{
"rfilename": "images/json_example.png"
},
{
"rfilename": "images/json_example_handwritten.png"
},
{
"rfilename": "images/overview.png"
},
{
"rfilename": "logo/Dharma-ai_logo_horizontal-black.png"
},
{
"rfilename": "logo/Dharma-ai_logo_horizontal-white.png"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model-00001-of-00002.safetensors"
},
{
"rfilename": "model-00002-of-00002.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "recipe.yaml"
},
{
"rfilename": "special_tokens_map.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "video_preprocessor_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [],
"tags": [
"transformers",
"safetensors",
"qwen2_5_vl",
"image-text-to-text",
"ocr",
"document-understanding",
"structured-extraction",
"specialized-small-language-model",
"brazilian-portuguese",
"conversational",
"pt",
"dataset:dharma-ai/DharmaOCR-Benchmark",
"arxiv:2604.14314",
"license:other",
"text-generation-inference",
"endpoints_compatible",
"compressed-tensors",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 5370548952
} | ||||||
|---|---|---|---|---|---|---|---|
| downloads | 370receipt
What the source handed over{
"_asked": "Dharma-AI/Dharma-OCR-LITE",
"_id": "69c875c8fc5631a422c50143",
"author": "Dharma-AI",
"cardData": {
"datasets": [
"dharma-ai/DharmaOCR-Benchmark"
],
"language": [
"pt"
],
"library_name": "transformers",
"license": "other",
"license_link": "LICENSE",
"license_name": "dharmaocr-lite-license",
"pipeline_tag": "image-text-to-text",
"tags": [
"ocr",
"document-understanding",
"structured-extraction",
"specialized-small-language-model",
"brazilian-portuguese"
]
},
"config": {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"chat_template_jinja": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or (('image' in content or 'image_url' in content) and content['type'] != 'text') %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
"model_type": "qwen2_5_vl",
"quantization_config": {
"config_groups": {
"group_0": {
"format": "float-quantized",
"targets": [
"Linear"
],
"weights": {
"num_bits": 8
}
}
},
"format": "float-quantized",
"quant_method": "compressed-tensors"
},
"tokenizer_config": {
"bos_token": null,
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2026-03-29T00:43:52.000Z",
"disabled": false,
"downloads": 370,
"gated": false,
"id": "Dharma-AI/Dharma-OCR-LITE",
"lastModified": "2026-04-17T12:10:30.000Z",
"library_name": "transformers",
"likes": 22,
"model-index": null,
"modelId": "Dharma-AI/Dharma-OCR-LITE",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"BF16": 1291256312,
"F8_E4M3": 2774532096
},
"total": 4065788408
},
"sha": "3fd38b0c131fffc7c812e70bab626a317d96ef57",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "NOTICE.txt"
},
{
"rfilename": "README.md"
},
{
"rfilename": "added_tokens.json"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "images/cost_x_score.png"
},
{
"rfilename": "images/example_text_degeneration.png"
},
{
"rfilename": "images/json_example.png"
},
{
"rfilename": "images/json_example_handwritten.png"
},
{
"rfilename": "images/overview.png"
},
{
"rfilename": "logo/Dharma-ai_logo_horizontal-black.png"
},
{
"rfilename": "logo/Dharma-ai_logo_horizontal-white.png"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model-00001-of-00002.safetensors"
},
{
"rfilename": "model-00002-of-00002.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "recipe.yaml"
},
{
"rfilename": "special_tokens_map.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "video_preprocessor_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [],
"tags": [
"transformers",
"safetensors",
"qwen2_5_vl",
"image-text-to-text",
"ocr",
"document-understanding",
"structured-extraction",
"specialized-small-language-model",
"brazilian-portuguese",
"conversational",
"pt",
"dataset:dharma-ai/DharmaOCR-Benchmark",
"arxiv:2604.14314",
"license:other",
"text-generation-inference",
"endpoints_compatible",
"compressed-tensors",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 5370548952
} | ||||||
| gated | falsereceipt
What the source handed over{
"_asked": "Dharma-AI/Dharma-OCR-LITE",
"_id": "69c875c8fc5631a422c50143",
"author": "Dharma-AI",
"cardData": {
"datasets": [
"dharma-ai/DharmaOCR-Benchmark"
],
"language": [
"pt"
],
"library_name": "transformers",
"license": "other",
"license_link": "LICENSE",
"license_name": "dharmaocr-lite-license",
"pipeline_tag": "image-text-to-text",
"tags": [
"ocr",
"document-understanding",
"structured-extraction",
"specialized-small-language-model",
"brazilian-portuguese"
]
},
"config": {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"chat_template_jinja": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or (('image' in content or 'image_url' in content) and content['type'] != 'text') %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
"model_type": "qwen2_5_vl",
"quantization_config": {
"config_groups": {
"group_0": {
"format": "float-quantized",
"targets": [
"Linear"
],
"weights": {
"num_bits": 8
}
}
},
"format": "float-quantized",
"quant_method": "compressed-tensors"
},
"tokenizer_config": {
"bos_token": null,
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2026-03-29T00:43:52.000Z",
"disabled": false,
"downloads": 370,
"gated": false,
"id": "Dharma-AI/Dharma-OCR-LITE",
"lastModified": "2026-04-17T12:10:30.000Z",
"library_name": "transformers",
"likes": 22,
"model-index": null,
"modelId": "Dharma-AI/Dharma-OCR-LITE",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"BF16": 1291256312,
"F8_E4M3": 2774532096
},
"total": 4065788408
},
"sha": "3fd38b0c131fffc7c812e70bab626a317d96ef57",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "NOTICE.txt"
},
{
"rfilename": "README.md"
},
{
"rfilename": "added_tokens.json"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "images/cost_x_score.png"
},
{
"rfilename": "images/example_text_degeneration.png"
},
{
"rfilename": "images/json_example.png"
},
{
"rfilename": "images/json_example_handwritten.png"
},
{
"rfilename": "images/overview.png"
},
{
"rfilename": "logo/Dharma-ai_logo_horizontal-black.png"
},
{
"rfilename": "logo/Dharma-ai_logo_horizontal-white.png"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model-00001-of-00002.safetensors"
},
{
"rfilename": "model-00002-of-00002.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "recipe.yaml"
},
{
"rfilename": "special_tokens_map.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "video_preprocessor_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [],
"tags": [
"transformers",
"safetensors",
"qwen2_5_vl",
"image-text-to-text",
"ocr",
"document-understanding",
"structured-extraction",
"specialized-small-language-model",
"brazilian-portuguese",
"conversational",
"pt",
"dataset:dharma-ai/DharmaOCR-Benchmark",
"arxiv:2604.14314",
"license:other",
"text-generation-inference",
"endpoints_compatible",
"compressed-tensors",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 5370548952
} | ||||||
| licence | otherreceipt
What the source handed over{
"_asked": "Dharma-AI/Dharma-OCR-LITE",
"_id": "69c875c8fc5631a422c50143",
"author": "Dharma-AI",
"cardData": {
"datasets": [
"dharma-ai/DharmaOCR-Benchmark"
],
"language": [
"pt"
],
"library_name": "transformers",
"license": "other",
"license_link": "LICENSE",
"license_name": "dharmaocr-lite-license",
"pipeline_tag": "image-text-to-text",
"tags": [
"ocr",
"document-understanding",
"structured-extraction",
"specialized-small-language-model",
"brazilian-portuguese"
]
},
"config": {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"chat_template_jinja": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or (('image' in content or 'image_url' in content) and content['type'] != 'text') %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
"model_type": "qwen2_5_vl",
"quantization_config": {
"config_groups": {
"group_0": {
"format": "float-quantized",
"targets": [
"Linear"
],
"weights": {
"num_bits": 8
}
}
},
"format": "float-quantized",
"quant_method": "compressed-tensors"
},
"tokenizer_config": {
"bos_token": null,
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2026-03-29T00:43:52.000Z",
"disabled": false,
"downloads": 370,
"gated": false,
"id": "Dharma-AI/Dharma-OCR-LITE",
"lastModified": "2026-04-17T12:10:30.000Z",
"library_name": "transformers",
"likes": 22,
"model-index": null,
"modelId": "Dharma-AI/Dharma-OCR-LITE",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"BF16": 1291256312,
"F8_E4M3": 2774532096
},
"total": 4065788408
},
"sha": "3fd38b0c131fffc7c812e70bab626a317d96ef57",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "NOTICE.txt"
},
{
"rfilename": "README.md"
},
{
"rfilename": "added_tokens.json"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "images/cost_x_score.png"
},
{
"rfilename": "images/example_text_degeneration.png"
},
{
"rfilename": "images/json_example.png"
},
{
"rfilename": "images/json_example_handwritten.png"
},
{
"rfilename": "images/overview.png"
},
{
"rfilename": "logo/Dharma-ai_logo_horizontal-black.png"
},
{
"rfilename": "logo/Dharma-ai_logo_horizontal-white.png"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model-00001-of-00002.safetensors"
},
{
"rfilename": "model-00002-of-00002.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "recipe.yaml"
},
{
"rfilename": "special_tokens_map.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "video_preprocessor_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [],
"tags": [
"transformers",
"safetensors",
"qwen2_5_vl",
"image-text-to-text",
"ocr",
"document-understanding",
"structured-extraction",
"specialized-small-language-model",
"brazilian-portuguese",
"conversational",
"pt",
"dataset:dharma-ai/DharmaOCR-Benchmark",
"arxiv:2604.14314",
"license:other",
"text-generation-inference",
"endpoints_compatible",
"compressed-tensors",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 5370548952
} | ||||||
| likes | 22receipt
What the source handed over{
"_asked": "Dharma-AI/Dharma-OCR-LITE",
"_id": "69c875c8fc5631a422c50143",
"author": "Dharma-AI",
"cardData": {
"datasets": [
"dharma-ai/DharmaOCR-Benchmark"
],
"language": [
"pt"
],
"library_name": "transformers",
"license": "other",
"license_link": "LICENSE",
"license_name": "dharmaocr-lite-license",
"pipeline_tag": "image-text-to-text",
"tags": [
"ocr",
"document-understanding",
"structured-extraction",
"specialized-small-language-model",
"brazilian-portuguese"
]
},
"config": {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"chat_template_jinja": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or (('image' in content or 'image_url' in content) and content['type'] != 'text') %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
"model_type": "qwen2_5_vl",
"quantization_config": {
"config_groups": {
"group_0": {
"format": "float-quantized",
"targets": [
"Linear"
],
"weights": {
"num_bits": 8
}
}
},
"format": "float-quantized",
"quant_method": "compressed-tensors"
},
"tokenizer_config": {
"bos_token": null,
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2026-03-29T00:43:52.000Z",
"disabled": false,
"downloads": 370,
"gated": false,
"id": "Dharma-AI/Dharma-OCR-LITE",
"lastModified": "2026-04-17T12:10:30.000Z",
"library_name": "transformers",
"likes": 22,
"model-index": null,
"modelId": "Dharma-AI/Dharma-OCR-LITE",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"BF16": 1291256312,
"F8_E4M3": 2774532096
},
"total": 4065788408
},
"sha": "3fd38b0c131fffc7c812e70bab626a317d96ef57",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "NOTICE.txt"
},
{
"rfilename": "README.md"
},
{
"rfilename": "added_tokens.json"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "images/cost_x_score.png"
},
{
"rfilename": "images/example_text_degeneration.png"
},
{
"rfilename": "images/json_example.png"
},
{
"rfilename": "images/json_example_handwritten.png"
},
{
"rfilename": "images/overview.png"
},
{
"rfilename": "logo/Dharma-ai_logo_horizontal-black.png"
},
{
"rfilename": "logo/Dharma-ai_logo_horizontal-white.png"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model-00001-of-00002.safetensors"
},
{
"rfilename": "model-00002-of-00002.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "recipe.yaml"
},
{
"rfilename": "special_tokens_map.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "video_preprocessor_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [],
"tags": [
"transformers",
"safetensors",
"qwen2_5_vl",
"image-text-to-text",
"ocr",
"document-understanding",
"structured-extraction",
"specialized-small-language-model",
"brazilian-portuguese",
"conversational",
"pt",
"dataset:dharma-ai/DharmaOCR-Benchmark",
"arxiv:2604.14314",
"license:other",
"text-generation-inference",
"endpoints_compatible",
"compressed-tensors",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 5370548952
} | ||||||
| task | image-text-to-textreceipt
What the source handed over{
"_asked": "Dharma-AI/Dharma-OCR-LITE",
"_id": "69c875c8fc5631a422c50143",
"author": "Dharma-AI",
"cardData": {
"datasets": [
"dharma-ai/DharmaOCR-Benchmark"
],
"language": [
"pt"
],
"library_name": "transformers",
"license": "other",
"license_link": "LICENSE",
"license_name": "dharmaocr-lite-license",
"pipeline_tag": "image-text-to-text",
"tags": [
"ocr",
"document-understanding",
"structured-extraction",
"specialized-small-language-model",
"brazilian-portuguese"
]
},
"config": {
"architectures": [
"Qwen2_5_VLForConditionalGeneration"
],
"chat_template_jinja": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or (('image' in content or 'image_url' in content) and content['type'] != 'text') %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
"model_type": "qwen2_5_vl",
"quantization_config": {
"config_groups": {
"group_0": {
"format": "float-quantized",
"targets": [
"Linear"
],
"weights": {
"num_bits": 8
}
}
},
"format": "float-quantized",
"quant_method": "compressed-tensors"
},
"tokenizer_config": {
"bos_token": null,
"eos_token": "<|im_end|>",
"pad_token": "<|endoftext|>",
"unk_token": null
}
},
"createdAt": "2026-03-29T00:43:52.000Z",
"disabled": false,
"downloads": 370,
"gated": false,
"id": "Dharma-AI/Dharma-OCR-LITE",
"lastModified": "2026-04-17T12:10:30.000Z",
"library_name": "transformers",
"likes": 22,
"model-index": null,
"modelId": "Dharma-AI/Dharma-OCR-LITE",
"pipeline_tag": "image-text-to-text",
"private": false,
"safetensors": {
"parameters": {
"BF16": 1291256312,
"F8_E4M3": 2774532096
},
"total": 4065788408
},
"sha": "3fd38b0c131fffc7c812e70bab626a317d96ef57",
"siblings": [
{
"rfilename": ".gitattributes"
},
{
"rfilename": "LICENSE"
},
{
"rfilename": "NOTICE.txt"
},
{
"rfilename": "README.md"
},
{
"rfilename": "added_tokens.json"
},
{
"rfilename": "chat_template.jinja"
},
{
"rfilename": "config.json"
},
{
"rfilename": "generation_config.json"
},
{
"rfilename": "images/cost_x_score.png"
},
{
"rfilename": "images/example_text_degeneration.png"
},
{
"rfilename": "images/json_example.png"
},
{
"rfilename": "images/json_example_handwritten.png"
},
{
"rfilename": "images/overview.png"
},
{
"rfilename": "logo/Dharma-ai_logo_horizontal-black.png"
},
{
"rfilename": "logo/Dharma-ai_logo_horizontal-white.png"
},
{
"rfilename": "merges.txt"
},
{
"rfilename": "model-00001-of-00002.safetensors"
},
{
"rfilename": "model-00002-of-00002.safetensors"
},
{
"rfilename": "model.safetensors.index.json"
},
{
"rfilename": "preprocessor_config.json"
},
{
"rfilename": "recipe.yaml"
},
{
"rfilename": "special_tokens_map.json"
},
{
"rfilename": "tokenizer.json"
},
{
"rfilename": "tokenizer_config.json"
},
{
"rfilename": "video_preprocessor_config.json"
},
{
"rfilename": "vocab.json"
}
],
"spaces": [],
"tags": [
"transformers",
"safetensors",
"qwen2_5_vl",
"image-text-to-text",
"ocr",
"document-understanding",
"structured-extraction",
"specialized-small-language-model",
"brazilian-portuguese",
"conversational",
"pt",
"dataset:dharma-ai/DharmaOCR-Benchmark",
"arxiv:2604.14314",
"license:other",
"text-generation-inference",
"endpoints_compatible",
"compressed-tensors",
"region:us"
],
"transformersInfo": {
"auto_model": "AutoModelForMultimodalLM",
"pipeline_tag": "image-text-to-text",
"processor": "AutoProcessor"
},
"usedStorage": 5370548952
} |
Text
This source's terms allow its title, its values and a link here, not its text. It is at https://huggingface.co/Dharma-AI/Dharma-OCR-LITE.