datalab-to/chandra-ocr-2
image-text-to-text model by datalab-to
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.
Chandra 2 is a state of the art OCR model from Datalab that outputs markdown, HTML, and JSON. It is highly accurate at extracting text from images and PDFs, while preserving layout information. Try Chandra in the free playground, or use the hosted API for higher accuracy and speed. The table below covers the 43 most common languages, benchmarked across multiple models. For a comprehensive evaluation across 90 languages (Chandra 2 vs Gemini 2.5 Flash only), see the full 90-language benchmark. We also have a more comprehensive evaluation covering 90 languages, comparing Chandra 2 against Gemini 2.5 Flash. The average scores are lower than the 43-language table above because this includes many lower-resource languages. Chandra 2 averages 72.7% vs Gemini 2.5 Flash at…
Read the full model card ↗ · Preview checked 2026-10-29T07:30:56.537Z
Inside the original model card — Document outline
- Chandra OCR 2
- What's New in Chandra 2
- Features
- Quickstart
- Usage
- With vLLM (recommended)
- With HuggingFace Transformers
- Benchmarks
- olmOCR Benchmark
- Examples
- Multilingual Benchmark (43 Languages)
- Full 90-Language Benchmark
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: openrail. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
datalab-to/chandra-ocr-2 is a image-text-to-text model repository published by datalab-to 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)
- 1,416,975
- Cumulative likes
- 593
- Hugging Face trending score
- 17
- Reported safetensors parameters
- 5,295,564,288
- Architecture
- Qwen3_5ForConditionalGeneration
- License
- openrail
- Access
- Not gated by Hugging Face
- Created
- 2026-03-16T20:47:07.000Z
- Last modified
- 2026-06-26T10:30:43.000Z
Compatibility and lineage
Language coverage was not reported.
Base-model lineage was not included.
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.