Baidu's Unlimited-OCR repo hits 31.9k GitHub stars, MIT-licensed with paper on arXiv
abhishek__AI · x · 2026-11-23
The GitHub repo for Baidu's Unlimited OCR2 (baidu/Unlimited-OCR) has reached 31.9k stars and 3.4k forks, released under the MIT license. The timeline shows the paper is on arXiv (early November), the model is live on ModelScope, HuggingFace and Baidu AI Cloud with a web entry at TextMind, and the ms-swift community already supports training it. The repo includes an inference script (infer.py) and PDFs of both paper editions.
Related event: Baidu Open-Sources Unlimited OCR2 for Book-Length Document Parsing(2 posts)→
More from Models
- Do Emotions Drive Agent Behavior? Speculation That Blocking Strong Feelings Constrains Agency — mimi10v3 · 2026-11-23
- Writers Push Google for Gemini 18+ Age Verification and Content Toggles to Stop Exodus to Grok — Hikkynure · 2026-11-23
- Qwen4-Max launches as a weights-off hosted preview, while free open Qwen models span every device — alex_verem · 2026-11-23
- Inkling-2-Mini GPTQ Quant Ships 524K-Token Context in One 18.3GB File on a Single 24GB Card — W61k3r · 2026-11-23
- Uncensored 26.4B model runs on a 12GB Mac at 85 tok/s with 8 parallel agents via Locals — SumitGup · 2026-11-23
- Princeton's SSoN Benchmark: Best Vision Model Scores 39.7% vs Human 83.3% on Spatial Consistency — jiqizhixin · 2026-11-23