jinaai/jina-ocr-v1
image-text-to-text model by jinaai
Older snapshot: check the original source for current information.
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.
Blog | Reader | Playground | AWS | Azure | GCP | Arxiv jina-ocr-v1 is an end-to-end document parsing model designed for high-quality OCR at an efficient serving point. The model builds on DeepSeek-OCR and inherits two of its efficiency-oriented components: a DeepEncoder vision tower that represents a 1024×1024 global view with 256 visual tokens and augments it with dynamic local tiles, and a 3B-parameter mixture-of-experts decoder with approximately 570M active parameters per token. On top of this backbone, we add a FastMTP speculative decoding head that recursively shares one dense draft block across K=3 prediction steps. Greedy verification accepts the longest token-equality prefix, preserving the verifier’s greedy output sequence by construction. This repository ships the model weights and the custom code needed to load them (trustremotecode=True). There is no separate training or serving package to install. Transformers uses the modeling files in this snapshot; vLLM needs a one-time architecture…
Read the full model card ↗ · Preview checked 2026-10-29T20:58:20.406Z
Inside the original model card — Document outline
- Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Reward-Dense Post-Training
- Performance
- Prompt
- Jina Reader
- Hosted API
- Playground
- Transformers
- vLLM (FastMTP)
- Citation
- License
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: cc-by-nc-4.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
jinaai/jina-ocr-v1 is a image-text-to-text model repository published by jinaai 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)
- 5,920
- Cumulative likes
- 182
- Hugging Face trending score
- 60
- Reported safetensors parameters
- 3,372,238,080
- Architecture
- DeepseekOCRForCausalLM
- License
- cc-by-nc-4.0
- Access
- Not gated by Hugging Face
- Created
- 2026-09-01T07:55:38.000Z
- Last modified
- 2026-09-18T04:37:12.000Z
Compatibility and lineage
Reported languages: multilingual
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 2026-09-28T06:37:58.127Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.