sahilchachra/Unlimited-OCR-AWQ
image-text-to-text model by sahilchachra
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
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. Unlimited-OCR uses the DeepSeek-OCR prompt vocabulary. The prompt must contain ; prefix it with whenever you also want bounding boxes for what was read. or large/high-resolution documents. With , 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 ... tags if you only want text, or parse them to overlay boxes / rebuild layout. Without you get plain text (or Markdown) with no box tags. The original model ships an SGLang wheel and a vLLM path (see…
Read the full model card ↗ · Preview checked 2026-10-30T03:56:24.726Z
Inside the original model card — Document outline
- Unlimited-OCR — AWQ (W4A16)
- This quant
- Quick start
- Prompting guide
- Resolution modes
- Understanding the output (grounding tokens)
- Serving
- About the model
- How this was made
- Verified
- Limitations
- Other formats
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: mit. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
sahilchachra/Unlimited-OCR-AWQ is a image-text-to-text model repository published by sahilchachra on Hugging Face. The source reports the transformers library.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- image-text-to-text
- Library
- transformers
- Recent downloads (30 days)
- 770,559
- Cumulative likes
- 16
- Hugging Face trending score
- 0
- Reported safetensors parameters
- 3,356,377,127
- Architecture
- UnlimitedOCRForCausalLM
- License
- mit
- Access
- Not gated by Hugging Face
- Created
- 2026-06-23T06:21:21.000Z
- Last modified
- 2026-06-23T06:22:31.000Z
Compatibility and lineage
Reported languages: multilingual
Reported base models: baidu/Unlimited-OCR
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:51:30.840Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.