长PDF要是拆成单页再往一块拼，跨页表格和阅读顺序十有八九会乱套，这事你八成也烦过。
This is a dev post classified by AGK Intelligence as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
长PDF要是拆成单页再往一块拼，跨页表格和阅读顺序十有八九会乱套，这事你八成也烦过。 百度开源的Unlimited-OCR打算多页一起塞进去：参数约30亿、激活量压得更低，论文里在32K上下文下能一口气解几十页，OmniDocBench上的成绩比DeepSeek-OCR那条基线还高。 它跑在本机，权重公开。Transformers、vLLM可以对接，社区那边也在跟进llama.cpp。云OCR按页数收钱，这东西等于把开销换成了机器和时间。 至于100页能不能一口吞完，得看显存和文档密度，仓库可没给你写保底。合同、论文先在本地过一轮没问题，终稿仍旧得人盯着。 🔗https://github.com/baidu/Unlimited-OCR
Posted by lumxss (33k followers) 1 h ago · 0 likes · 112 views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: unlimited-ocr.
More dev work like this
- Your agents are burning frontier tokens on simple yes/no questions. — @PixelRainbowNFT
- Arena CEO Anastasios Angelopoulos, whose platform benchmarks AI models, on a $40 “thank… — @8teAPi
- Most people who want to rebuild something start by staring at the original, plopping it… — @PixelRainbowNFT
- Today we're introducing Extract Max Effort - the best frontier agent in the world for… — @jerryjliu0
- Local models on Apple Silicon finally feel like a product, not a weekend project. — @PixelRainbowNFT
- GPT 6.1 Terra max vs GPT 6.1 Sol max — @HarshithLucky3
- Asked at the Meetup: "Does sbx run mistral work?" — @ajeetsraina
- Most agents freeze once deployed. — @GoogleCloudTech
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.2k posts from 5k X accounts over the last 21 days, 8.8k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-10-30 23:02 UTC. Full method.