Baidu's Unlimited-OCR repo hits 28.9k stars with inference code and tech report
abhishek__AI · x · 2026-10-27
This is the GitHub release post for Baidu's Unlimited OCR 2. The repo baidu/Unlimited-OCR is MIT-licensed and has reached 28.9k stars and 3.1k forks.
- Includes an inference script (infer.py), the tech report PDF (Unlimited-OCR-2.pdf), wheels and utilities
- Timeline: Hugging Face demo and vLLM support in June 2026, ms-swift training support and Baidu Cloud availability in July, and the v2 release with unlimited-horizon parsing on Oct 27, 2026
- The model parses hundreds of pages per request with near-constant decoding latency via SR-SWA
Related event: Baidu Open-Sources Unlimited OCR 2 for Thousand-Page Document Parsing(21 posts)→
More from Models
- inclusionAI's Ling-3.1-flash-1019: 560B MoE, 25B active, 1M context, AA score up to 44 — jacek2023 · 2026-10-27
- User shows Gemini ignoring explicit custom instructions and starting actions unbidden — loriofficialita · 2026-10-27
- EdgeRock architecture keeps KV cache at 72 MiB for 256K context, 99.1% smaller than Qwen3.5-4B — alifcoder · 2026-10-27
- Dev Who Called Kimi Subscription a Scam Gets Locked Out Over False Paid-Post Flag — Scobleizer · 2026-10-27
- Blogger reverses stance: Anthropic now 'crushes' OpenAI models, opposite of 3 months ago — Scobleizer · 2026-10-27
- Power user's stress test: ChatGPT great at research, flaky at image consistency — andytechuk · 2026-10-27