blank

@AdinaYakup @huggingface @xiaohongshu Can anyone setup space for this

Another OCR model just dropped on @huggingface (so many OCRs lately!) dots.mocr from @xiaohongshu Hi Lab looks really impressive on the benchmarks. -Model: huggingface.co/collections/re… -Paper: huggingface.co/papers/2603.13… ✨ 3B ✨ Multilingual support ✨ Converts charts, diagrams, and UI layouts directly into SVG code

@PaddlePaddle Dm me I want to share urdu datasets with you because your model is useless for urdu documents

🚀 Big Upgrade: PaddleOCR Website Just Got a Major Boost! More pages. Faster parsing. Better batch workflows. The latest PaddleOCR website update is built for real-world document workloads — from long PDFs to high-volume processing. What’s new 📄 10,000 free pages/day for individual users ⏱️ New async parsing service for long documents and heavy jobs 📚 Up to 1,000 pages per file — no more splitting large PDFs ⚙️ Stronger concurrency & batch processing with a major backend upgrade Why it matters With async service and higher throughput, PaddleOCR now handles long and large-scale document parsing far more efficiently — making enterprise-grade OCR workflows easier to access, test, and scale. 🌐 Try it now: paddleocr.com 💬 Feedback: paddleocr@baidu.com 🔧 GitHub: github.com/PaddlePaddle/P… And with PaddleOCR Skills already live on ClawHub, your OpenClaw workflows can now process documents even faster and better.💪 #PaddleOCR #OCR #DocumentAI #OpenSource #ClawHub

@VikParuchuri Very bad with urdu docs I got datasets dm me I send u folder link

I'm excited to open source Chandra OCR 2! - 85.9% (sota) on olmocr bench - 90+ language support w/benchmarks - 4B model (down from 9B) - Full layout information - Extracts + captions images and diagrams - Strong handwriting, math, form, table support

@MENAUnleashed Share list

I have successfully cleansed my account of indians. i live in peace again. I have blocked 100 accounts or so.

@vanstriendaniel @rednotehilab @huggingface Best model I test my language urdu handwritten notes and it improves alot from previous version I shared those urdu datasets with its developer other models are way behind latest glm ocr is shit in urdu documents

dots.ocr-1.5 from @rednotehilab wasn't on @huggingface yet, so I mirrored it from ModelScope 3B OCR model: - 83.9% olmOCR-bench - Web/scene text parsing - 100+ languages, MIT-based Ready-to-run UV script included huggingface.co/davanstrien/do…

@Zai_org It's totally disappointing in urdu language documents u guys didn't train in urdu datasets

GLM-OCR has accumulated over 3M downloads. We are releasing its technical report: arxiv.org/abs/2603.10910 We welcome your feedback!

@daniel_mac8 Sleeping

WHERE TF IS DEEPSEEK-V4?

@IntCyberDigest That is fake

‼️ Very interesting: Iran's newly elected Supreme Leader Ayatollah Mojtaba Khamenei's account appears to be based in the Netherlands 👀

@BlinkzSec Link is broken do u have all files zip

Why does this Russian support technician want to disable my antivirus? Well, I'll leave it at that. telegram bot token: 8617483102:AAGkFE-x8Z81Ex-PtnzkMURy1-1CI3KGpdU $CHAT_ID = "-5185728008" bazaar.abuse.ch/sample/d756d1e… #opendir

@clashreport Big mistake they got golden chance to change there life

One of the seven members of the Iranian women’s football team delegation who was granted asylum in Australia has changed her mind and asked to return to Iran. The player initially chose to stay in Brisbane but later contacted the Iranian embassy after speaking with teammates who had already left. Australian Home Affairs Minister Tony Burke said officials confirmed the decision was voluntary and arranged for her return. Source: Australian Broadcasting Corporation

@soldierspeaks Nice joke 🤣

پاکستان نے ایران فون کرکے امریکی و اسرائیلی حملے کی مذمت کی ہے جبکہ سعودی عرب فون کرکے ایرانی حملے کی۔ پاکستان نے کہا ہے کہ وہ امریکی حملے کے خلاف ایران کے ساتھ کھڑا ہے جبکہ ایرانی حملے کے خلاف سعودی عرب کے ساتھ۔ بیان دیکھ کر ایران و سعودی عرب دونوں نے کھڑے ہونے پر پاکستان کا شکریہ ادا کیا اور اسے بیٹھ جانے کو کہا. (منقول)

@vanstriendaniel @huggingface Which model u use

Is it worth re-OCR'ing old library index cards? Re-OCR'd 453,000 from Boston Public Library's rare books catalogue. ~$50 compute using @huggingface Jobs BPL's own guide calls their search "extremely unreliable." Does better OCR and semantic search fix it? Demo link below

@support_huihui Demo space any one can setup give me link

New Model: huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated This is an uncensored version of Qwen/Qwen3.5-35B-A3B created with abliteration huggingface.co/huihui-ai/Huih…

@vanstriendaniel Only dots. Ocr latest will work make post if some one downloaded 1.5 they have model files to share with you

Everyone kept telling me Gemini Pro would do a perfect job but the results are not that great. Scaling this to millions of pages would also be insanely expensive and slow.

@vanstriendaniel @huggingface Try dots.ocr

Ran the same OCR models on 68 pages of historic newspaper. Every model hallucinated or looped. DeepSeek-OCR-2, LightOnOCR-2, GLM-OCR – all melt down on dense newspaper columns. You can try yourself using this @huggingface dataset: huggingface.co/datasets/davan…

@mountainaddict0 Link?

While others use manual tools for recon or run Google dorks to find leaked data on target websites, this AI tool does everything by itself. You just provide the web link & ask it to look for leaked IDs or any exposed information. It automatically searches the internet .

Here is how I find someone’s deleted Tweets on X/Twitter 🐦💻 I used to manually search for someone’s username across search engines 🔍, hoping to find a cached tweet 🗂️ Recently, a new website allows you to automatically search for cached tweets across multiple search engines and archival services ⚡🌐 The tool is called Deleted Tweet Finder V2.3 🛠️ You can access it here: 🌐 cache.digitaldigging.org Here’s how to use it: 1. Visit the website 🖥️ 2. Enter the person’s X/Twitter URL or the URL of a tweet they made 🔗 3. Select the service ✅ 4. Click on “Go” ▶️ This will open a new tab with the service you selected and search for the profile or tweet 🗂️🔎 Note ⚠️: Since X acquired Twitter, it’s recommended to search for a tweet/profile using both the x.com and x.com domain names 🌐 Example: Username: cyber_sudo 🧑‍💻 First URL: x.com/cyber_sudo Second URL: x.com/cyber_sudo ____________________ P.S. ♻️ Repost if you found this helpful. If you liked this post, get weekly OSINT tips by joining the OSINT Observer Newsletter, with over 5,000 OSINT enthusiasts: cybersudo.org. Plus, there’s a welcome gift waiting for you!

@naveedullah600 @ZenomTrader Naveed bro can u make mq5 indicator or semi auto ea from this nt8 code

AI agents are on another level. I asked Claude Code to build a Gold strategy in NinjaTrader 8 from scratch. It wrote the code, compiled it, debugged itself, ran the backtest, optimized it and delivered a profitable system. Fully autonomous. Very few are operating like this.

@AlvieriD Link.

Match, Hinge and OKCupid usage data leaked by ShinyHunters 10 million records released

@talkaboutdesign How setup with phone access can u share guide video

Just had Clawdbot set up Ollama with a local model. Now it handles website summaries and simple tasks locally instead of burning API credits. Blown away that an AI just installed another AI to save me money.