Unlimited-OCR

About

What Unlimited-OCR is

Unlimited-OCR — AWQ (W4A16) AWQ 4-bit (W4A16) quantization of baidu/Unlimited-OCR, a 3B vision-language OCR model that pushes DeepSeek-OCR one step further (one-shot, long-horizon document parsing). This repo quantizes the DeepSeek-V2 MoE text decoder with activation-aware scaling (AWQ) while keeping the vision tower in BF16, so it stays a drop-in transformers model. ⚠️ Runtime requirements. This is custom remote code, so load with trustremotecode=True, transformers 4.57.x, and compressed-tensors installed. W4A16 (int4) runs on any CUDA GPU; compressed-tensors handles the 4-bit unpacking at load. This quant Quick start Prompting guide Unlimited-OCR uses the DeepSeek-OCR prompt vocabulary. The prompt must contain <image; prefix it with <|grounding| whenever you also want bounding boxes for what was read. Resolution modes - base — basesize=1024, imagesize=1024, cropmode=False. Good default for normal pages. - gundam — basesize=1024, imagesize=640, cropmode=True. Tiles the page; use for dense or large/high-resolution documents. Understanding the output (grounding tokens) With <|grounding|, the model interleaves the recognized text with detection boxes: Each [x1, y1, x2, y2] is the bounding box (top-left → bottom-right) of that span, in the coordinate space of the model's input image. Drop the <|det|...<|/det| tags if you only want text, or parse them to overlay boxes / rebuild layout. Without <|grounding| you get plain text (or Markdown) with no box tags. Serving The original model ships an SGLang wheel and a vLLM path (see the base model card). W4A16 / compressed-tensors weights load directly in runtimes with compressed-tensors support (e.g. vLLM); otherwise use the transformers snippet above. About the model - Architecture: UnlimitedOCRForCausalLM (DeepSeek-OCR architecture) — a DeepEncoder vision tower (SAM-ViT-B + CLIP-L/14, 1024×1024 input, 16× downsample) → linear projector → DeepSeek-V2 MoE text decoder (12 layers, hidden 1280, 64 routed + 2 shared experts, 6 experts/token; layer 0 dense). - Task: multilingual OCR / document parsing — single image, multi-page, and PDF (one-shot long-horizon parsing). - License: MIT (inherited from the base model). How this w

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How language models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys sahilchachra-unlimited-ocr for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (sahilchachra-unlimited-ocr below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"sahilchachra-unlimited-ocr","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Licence

Open weights

Sources

Weights & code

Explore

More language models