# baidu/Unlimited-OCR

> Baidu's OCR model for document parsing: extracts text from single images, multi-page files and PDFs in one pass, supporting long context up to 32768 tokens.

- Magnitude: 4.9 out of 10 — Breakout
- Stars: 29,609 total · +95 stars measured 2026-10-29, 00:03–07:05 UTC, ≈ 312 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: MIT · Created: 2026-06-18 · Last push: 2026-10-28
- GitHub: https://github.com/baidu/Unlimited-OCR · Page: https://gitnova.dev/en/r/baidu/Unlimited-OCR

## Useful for

- Extract text from a PDF by converting pages to images with PyMuPDF
- Serve the model locally via vLLM or SGLang with an OpenAI-compatible API
- Fine-tune the model on custom data using ms-swift

## Why it’s here

- Star-counter measurements on 2026-10-29 (UTC), 00:03–07:05: 29514 → 29609 stars (+95). This is the change over that interval.
- Estimated end-of-day forecast: about +312 stars, using observed gains and the previous day.
- Over the last two days the pace is 2.7× that of the previous week and a half.
- Elevated gains were measured on the last 3 completed UTC days in a row. Continued growth is not guaranteed.
- GitHub Trending Python today: #5, +429 stars.
- About 51 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 3,157
- Issues and pull requests: 112
- Watchers: 163
- Average over the last week: 244 per day
- Usual pace: 92 per day
- Stars in the last hour (measured): 10

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-09-30 … 2026-10-29: 28, 42, 28, 25, 26, 24, 55, 34, 23, 27, 28, 143, 180, 171, 75, 165, 133, 84, 84, 70, 74, 163, 111, 70, 44, 109, 305, 560, 310, 95

## Magnitude by day, last 14 days

10-16 4.2, 10-17 3.7, 10-18 3.2, 10-19 3.1, 10-20 2.7, 10-21 3.5, 10-22 4.0, 10-23 3.2, 10-24 2.7, 10-25 2.3, 10-26 3.6, 10-27 5.8, 10-28 6.2, 10-29 5.0

## Spotted in now

- GitHub Trending Python today: #5, +429 stars

## More in this category

1. **togg53192-cmd/jailbreaks** — 8.0 · Breakout · Language models · +480 stars measured 2026-10-29, 00:02–07:05 UTC, ≈ 1,572 by evening
   A collection of 31 system prompts, persona locks, and AGENTS.md files for 25+ models (Claude, Gemini, Grok, GLM, DeepSeek, Kimi, Qwen, Gemma, GPT-OSS). Intended for research on how instruction hierarchies and policy overrides affect model…
   Full card: https://gitnova.dev/en/r/togg53192-cmd/jailbreaks.md
2. **OpenBMB/MiniCPM-OCR** — 6.5 · Early signal · Language models · Python · +127 stars measured 2026-10-29, 00:03–07:05 UTC, ≈ 363 by evening
   MiniCPM-OCR is an open-source OCR model family for parsing Chinese and English documents and PDFs into Markdown or JSON, with a 2B model (Jev) that scores recognition quality per region.
   Full card: https://gitnova.dev/en/r/OpenBMB/MiniCPM-OCR.md
3. **Edge0-AI/Edge0** — 6.5 · Breakout · Language models · Python · +577 stars measured 2026-10-29, 00:05–07:05 UTC, ≈ 1,306 by evening
   An open-source streaming MoE inference framework: expert weights are offloaded from SSD on demand while a trained prerouter predicts routing ahead of time. Runs on Apple Silicon via MLX and ships with two ready-to-run model tiers (35B and…
   Full card: https://gitnova.dev/en/r/Edge0-AI/Edge0.md
4. **thomasunise/casecite** — 5.9 · Early signal · Language models · Python · +30 stars measured 2026-10-29, 00:03–07:05 UTC, ≈ 90 by evening
   Self-hosted legal research platform: upload your firm's documents, ask questions with citations, review contracts, draft documents and research judges. Runs on your own infrastructure with your own API keys.
   Full card: https://gitnova.dev/en/r/thomasunise/casecite.md
5. **google-deepmind/detectorscope** — 5.5 · Early signal · Language models · Python · +14 stars measured 2026-10-29, 00:03–07:05 UTC, ≈ 75 by evening
   A toolkit for building AI-text detectors whose decisions are mechanistically grounded and auditable: each prediction is a sum of named features localized in the text. Built on sparse autoencoders and a concept bottleneck over the language…
   Full card: https://gitnova.dev/en/r/google-deepmind/detectorscope.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-10-29 07:17 UTC, updated every 30 minutes.