Dharma-AI/Dharma-OCR-LITE

hf Dharma-AI/Dharma-OCR-LITE 2 sources, 3 claims · Watch

What each source says

PropertySourceSaidMeans here
Author
author
not compared		GGUF quantisationsigorfk369
receipt
Source
GGUF quantisations
Its words
igorfk369
Read by
field:author
Said since
2026-09-29 09:50 UTC
Last answered
2026-10-04 18:16 UTC
Original
open at the source
What the source handed over
{
  "_id": "6aac8bc2d1c588c246af82e4",
  "author": "igorfk369",
  "cardData": {
    "base_model": [
      "Dharma-AI/Dharma-OCR-LITE"
    ],
    "language": [
      "pt"
    ],
    "library_name": "transformers",
    "license": "other",
    "license_link": "https://huggingface.co/Dharma-AI/Dharma-OCR-LITE/resolve/main/LICENSE",
    "license_name": "dharmaocr-lite-license",
    "pipeline_tag": "image-text-to-text",
    "tags": [
      "qwen2_5_vl",
      "ocr",
      "document-understanding",
      "structured-extraction",
      "specialized-small-language-model",
      "brazilian-portuguese",
      "conversational",
      "text-generation-inference",
      "compressed-tensors"
    ]
  },
  "createdAt": "2026-09-18T00:54:26.000Z",
  "downloads": 436,
  "gated": false,
  "id": "igorfk369/Dharma-OCR-LITE-gguf",
  "lastModified": "2026-09-19T12:32:14.000Z",
  "library_name": "transformers",
  "likes": 0,
  "modelId": "igorfk369/Dharma-OCR-LITE-gguf",
  "pipeline_tag": "image-text-to-text",
  "private": false,
  "sha": "385fba774a8be2a0262630e4567d820b59d4dc65",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "Dharma-OCR-LITE-IQ4_NL.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-Q4_K_M.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-Q5_K_M.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-Q6_K.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-Q8_0.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-bf16.gguf"
    },
    {
      "rfilename": "README.md"
    },
    {
      "rfilename": "mmproj-Dharma-OCR-LITE-bf16.gguf"
    }
  ],
  "tags": [
    "transformers",
    "gguf",
    "qwen2_5_vl",
    "ocr",
    "document-understanding",
    "structured-extraction",
    "specialized-small-language-model",
    "brazilian-portuguese",
    "conversational",
    "text-generation-inference",
    "compressed-tensors",
    "image-text-to-text",
    "pt",
    "base_model:Dharma-AI/Dharma-OCR-LITE",
    "base_model:quantized:Dharma-AI/Dharma-OCR-LITE",
    "license:other",
    "endpoints_compatible",
    "region:us"
  ]
}
—
Author
author
not compared		Hugging Face modelsDharma-AI
receipt
Source
Hugging Face models
Last answered
2026-10-04 18:21 UTC
Original
open at the source

This source has not kept a receipt for this claim yet. The next update that reads it will.

—
Base
base
GGUF quantisationsDharma-AI/Dharma-OCR-LITE
receipt
Source
GGUF quantisations
Its words
Dharma-AI/Dharma-OCR-LITE
Read by
field:cardData.base_model[]
Said since
2026-09-29 09:50 UTC
Last answered
2026-10-04 18:16 UTC
Original
open at the source
What the source handed over
{
  "_id": "6aac8bc2d1c588c246af82e4",
  "author": "igorfk369",
  "cardData": {
    "base_model": [
      "Dharma-AI/Dharma-OCR-LITE"
    ],
    "language": [
      "pt"
    ],
    "library_name": "transformers",
    "license": "other",
    "license_link": "https://huggingface.co/Dharma-AI/Dharma-OCR-LITE/resolve/main/LICENSE",
    "license_name": "dharmaocr-lite-license",
    "pipeline_tag": "image-text-to-text",
    "tags": [
      "qwen2_5_vl",
      "ocr",
      "document-understanding",
      "structured-extraction",
      "specialized-small-language-model",
      "brazilian-portuguese",
      "conversational",
      "text-generation-inference",
      "compressed-tensors"
    ]
  },
  "createdAt": "2026-09-18T00:54:26.000Z",
  "downloads": 436,
  "gated": false,
  "id": "igorfk369/Dharma-OCR-LITE-gguf",
  "lastModified": "2026-09-19T12:32:14.000Z",
  "library_name": "transformers",
  "likes": 0,
  "modelId": "igorfk369/Dharma-OCR-LITE-gguf",
  "pipeline_tag": "image-text-to-text",
  "private": false,
  "sha": "385fba774a8be2a0262630e4567d820b59d4dc65",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "Dharma-OCR-LITE-IQ4_NL.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-Q4_K_M.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-Q5_K_M.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-Q6_K.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-Q8_0.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-bf16.gguf"
    },
    {
      "rfilename": "README.md"
    },
    {
      "rfilename": "mmproj-Dharma-OCR-LITE-bf16.gguf"
    }
  ],
  "tags": [
    "transformers",
    "gguf",
    "qwen2_5_vl",
    "ocr",
    "document-understanding",
    "structured-extraction",
    "specialized-small-language-model",
    "brazilian-portuguese",
    "conversational",
    "text-generation-inference",
    "compressed-tensors",
    "image-text-to-text",
    "pt",
    "base_model:Dharma-AI/Dharma-OCR-LITE",
    "base_model:quantized:Dharma-AI/Dharma-OCR-LITE",
    "license:other",
    "endpoints_compatible",
    "region:us"
  ]
}
—
Downloads
downloads
not compared		GGUF quantisations436
receipt
Source
GGUF quantisations
Its words
436
Read by
field:downloads
Said since
2026-09-29 09:50 UTC
Last answered
2026-10-04 18:16 UTC
Original
open at the source
What the source handed over
{
  "_id": "6aac8bc2d1c588c246af82e4",
  "author": "igorfk369",
  "cardData": {
    "base_model": [
      "Dharma-AI/Dharma-OCR-LITE"
    ],
    "language": [
      "pt"
    ],
    "library_name": "transformers",
    "license": "other",
    "license_link": "https://huggingface.co/Dharma-AI/Dharma-OCR-LITE/resolve/main/LICENSE",
    "license_name": "dharmaocr-lite-license",
    "pipeline_tag": "image-text-to-text",
    "tags": [
      "qwen2_5_vl",
      "ocr",
      "document-understanding",
      "structured-extraction",
      "specialized-small-language-model",
      "brazilian-portuguese",
      "conversational",
      "text-generation-inference",
      "compressed-tensors"
    ]
  },
  "createdAt": "2026-09-18T00:54:26.000Z",
  "downloads": 436,
  "gated": false,
  "id": "igorfk369/Dharma-OCR-LITE-gguf",
  "lastModified": "2026-09-19T12:32:14.000Z",
  "library_name": "transformers",
  "likes": 0,
  "modelId": "igorfk369/Dharma-OCR-LITE-gguf",
  "pipeline_tag": "image-text-to-text",
  "private": false,
  "sha": "385fba774a8be2a0262630e4567d820b59d4dc65",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "Dharma-OCR-LITE-IQ4_NL.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-Q4_K_M.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-Q5_K_M.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-Q6_K.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-Q8_0.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-bf16.gguf"
    },
    {
      "rfilename": "README.md"
    },
    {
      "rfilename": "mmproj-Dharma-OCR-LITE-bf16.gguf"
    }
  ],
  "tags": [
    "transformers",
    "gguf",
    "qwen2_5_vl",
    "ocr",
    "document-understanding",
    "structured-extraction",
    "specialized-small-language-model",
    "brazilian-portuguese",
    "conversational",
    "text-generation-inference",
    "compressed-tensors",
    "image-text-to-text",
    "pt",
    "base_model:Dharma-AI/Dharma-OCR-LITE",
    "base_model:quantized:Dharma-AI/Dharma-OCR-LITE",
    "license:other",
    "endpoints_compatible",
    "region:us"
  ]
}
—
Downloads
downloads
not compared		Hugging Face models370
receipt
Source
Hugging Face models
Its words
370
Read by
field:downloads
Said since
2026-10-04 12:16 UTC
Last answered
2026-10-04 18:21 UTC
Original
open at the source
2026-10-04 12:16 UTC370
2026-10-03 18:10 UTC385
2026-10-02 12:02 UTC442
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
downloads
not compared		586
receipt
Source
Hugging Face models
Last answered
2026-10-04 18:21 UTC
Original
open at the source

This source has not kept a receipt for this claim yet. The next update that reads it will.

—
Gated
gated
Hugging Face modelsfalse
receipt
Source
Hugging Face models
Last answered
2026-10-04 18:21 UTC
Original
open at the source

This source has not kept a receipt for this claim yet. The next update that reads it will.

—
Licence
licence
GGUF quantisationsother
receipt
Source
GGUF quantisations
Its words
other
Read by
field:cardData.license
Said since
2026-09-29 09:50 UTC
Last answered
2026-10-04 18:16 UTC
Original
open at the source
What the source handed over
{
  "_id": "6aac8bc2d1c588c246af82e4",
  "author": "igorfk369",
  "cardData": {
    "base_model": [
      "Dharma-AI/Dharma-OCR-LITE"
    ],
    "language": [
      "pt"
    ],
    "library_name": "transformers",
    "license": "other",
    "license_link": "https://huggingface.co/Dharma-AI/Dharma-OCR-LITE/resolve/main/LICENSE",
    "license_name": "dharmaocr-lite-license",
    "pipeline_tag": "image-text-to-text",
    "tags": [
      "qwen2_5_vl",
      "ocr",
      "document-understanding",
      "structured-extraction",
      "specialized-small-language-model",
      "brazilian-portuguese",
      "conversational",
      "text-generation-inference",
      "compressed-tensors"
    ]
  },
  "createdAt": "2026-09-18T00:54:26.000Z",
  "downloads": 436,
  "gated": false,
  "id": "igorfk369/Dharma-OCR-LITE-gguf",
  "lastModified": "2026-09-19T12:32:14.000Z",
  "library_name": "transformers",
  "likes": 0,
  "modelId": "igorfk369/Dharma-OCR-LITE-gguf",
  "pipeline_tag": "image-text-to-text",
  "private": false,
  "sha": "385fba774a8be2a0262630e4567d820b59d4dc65",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "Dharma-OCR-LITE-IQ4_NL.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-Q4_K_M.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-Q5_K_M.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-Q6_K.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-Q8_0.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-bf16.gguf"
    },
    {
      "rfilename": "README.md"
    },
    {
      "rfilename": "mmproj-Dharma-OCR-LITE-bf16.gguf"
    }
  ],
  "tags": [
    "transformers",
    "gguf",
    "qwen2_5_vl",
    "ocr",
    "document-understanding",
    "structured-extraction",
    "specialized-small-language-model",
    "brazilian-portuguese",
    "conversational",
    "text-generation-inference",
    "compressed-tensors",
    "image-text-to-text",
    "pt",
    "base_model:Dharma-AI/Dharma-OCR-LITE",
    "base_model:quantized:Dharma-AI/Dharma-OCR-LITE",
    "license:other",
    "endpoints_compatible",
    "region:us"
  ]
}
—
Licence
licence
Hugging Face modelsother
receipt
Source
Hugging Face models
Last answered
2026-10-04 18:21 UTC
Original
open at the source

This source has not kept a receipt for this claim yet. The next update that reads it will.

—
Likes
likes
not compared		GGUF quantisations0
receipt
Source
GGUF quantisations
Its words
0
Read by
field:likes
Said since
2026-09-29 09:50 UTC
Last answered
2026-10-04 18:16 UTC
Original
open at the source
What the source handed over
{
  "_id": "6aac8bc2d1c588c246af82e4",
  "author": "igorfk369",
  "cardData": {
    "base_model": [
      "Dharma-AI/Dharma-OCR-LITE"
    ],
    "language": [
      "pt"
    ],
    "library_name": "transformers",
    "license": "other",
    "license_link": "https://huggingface.co/Dharma-AI/Dharma-OCR-LITE/resolve/main/LICENSE",
    "license_name": "dharmaocr-lite-license",
    "pipeline_tag": "image-text-to-text",
    "tags": [
      "qwen2_5_vl",
      "ocr",
      "document-understanding",
      "structured-extraction",
      "specialized-small-language-model",
      "brazilian-portuguese",
      "conversational",
      "text-generation-inference",
      "compressed-tensors"
    ]
  },
  "createdAt": "2026-09-18T00:54:26.000Z",
  "downloads": 436,
  "gated": false,
  "id": "igorfk369/Dharma-OCR-LITE-gguf",
  "lastModified": "2026-09-19T12:32:14.000Z",
  "library_name": "transformers",
  "likes": 0,
  "modelId": "igorfk369/Dharma-OCR-LITE-gguf",
  "pipeline_tag": "image-text-to-text",
  "private": false,
  "sha": "385fba774a8be2a0262630e4567d820b59d4dc65",
  "siblings": [
    {
      "rfilename": ".gitattributes"
    },
    {
      "rfilename": "Dharma-OCR-LITE-IQ4_NL.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-Q4_K_M.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-Q5_K_M.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-Q6_K.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-Q8_0.gguf"
    },
    {
      "rfilename": "Dharma-OCR-LITE-bf16.gguf"
    },
    {
      "rfilename": "README.md"
    },
    {
      "rfilename": "mmproj-Dharma-OCR-LITE-bf16.gguf"
    }
  ],
  "tags": [
    "transformers",
    "gguf",
    "qwen2_5_vl",
    "ocr",
    "document-understanding",
    "structured-extraction",
    "specialized-small-language-model",
    "brazilian-portuguese",
    "conversational",
    "text-generation-inference",
    "compressed-tensors",
    "image-text-to-text",
    "pt",
    "base_model:Dharma-AI/Dharma-OCR-LITE",
    "base_model:quantized:Dharma-AI/Dharma-OCR-LITE",
    "license:other",
    "endpoints_compatible",
    "region:us"
  ]
}
—
Likes
likes
not compared		Hugging Face models22
receipt
Source
Hugging Face models
Last answered
2026-10-04 18:21 UTC
Original
open at the source

This source has not kept a receipt for this claim yet. The next update that reads it will.

—
Task
task
Hugging Face modelsimage-text-to-text
receipt
Source
Hugging Face models
Last answered
2026-10-04 18:21 UTC
Original
open at the source

This source has not kept a receipt for this claim yet. The next update that reads it will.

—

model

Dharma-AI/Dharma-OCR-LITE
zetlyn/models-hf · 2026-03-29
author Dharma-AI downloads 586 gated false licence other likes 22 task image-text-to-text source
Dharma-AI/Dharma-OCR-LITE
zetlyn/models-hf · 2026-03-29
author Dharma-AI downloads 370 gated false licence other likes 22 task image-text-to-text source

quantisation

igorfk369/Dharma-OCR-LITE-gguf
zetlyn/models-gguf · 2026-09-18
author igorfk369 base Dharma-AI/Dharma-OCR-LITE downloads 436 licence other likes 0 source