Hugging Face

PDFMathTranslate 🔥 A project and gradio app for PDF scientific paper translation and bilingual comparison. 📊 Preserve formulas, charts, table of contents, and annotations. 🌐 Support multiple languages 🤖 Also supports command-line tool & Docker 👇 Useful links Gradio user interface available for community for free on Hugging Face Spaces: https://lnkd.in/gaCJiJag Available for free on official website: https://pdf2zh.com/ Code: https://lnkd.in/gkn346NA

Mini 𝚐𝚛𝚊𝚍𝚒𝚘-𝚠𝚎𝚋𝚛𝚝𝚌 release to let you customize the audio animation 🤩 Set the icon, background color, and pulse color all from python. This was one of our most popular requests - what else should we tackle? P.S. Kyutai 's moshi seems to be a history buff 🤓

🔥🔥 FlowEdit Gradio app is now live on Hugging Face: https://lnkd.in/gG7eXuBQ For reference, please check out our earlier post introducing the FlowEdit model: https://lnkd.in/gHDUHTct

Leffa from Meta is a 🆕 unified framework for Virtual try-on and Pose transfer!🔥 👕 Provides controllable person image generation that enables precise manipulation of both appearance (i.e., Virtual try-on) and pose (i.e., Pose transfer). Learn more about 📚 Code,🔥 Demo, and 🤗 Model ⬇️ > Leffa Model on Hugging Face Hub with MIT license: https://lnkd.in/gfFWcsCF > Build Leffa for VirtualTryOn and Pose Transfer locally with Gradio: https://lnkd.in/gcnezZrW > Leffa Gradio app is up on Hugging Face Spaces: https://lnkd.in/gdnuNTHv

Sun never sets for the Diffusers team 🤗🌞 Presenting our latest integration of LTX by Lightricks - a superior video generation model at its scale. It produces 24 FPS videos at a 768x512 resolution faster than they can be watched 🤪 Model is pretty consumer-friendly, but in case not, you should be able to leverage all the diffusers goodies to make it run on your machine! Kudos to Aryan V S, who led this integration. Next up is -- a script for ___ LTX 🚀 Wrong answers only 🪄 Check it out here: https://lnkd.in/gwMKniDN

It is raining open-source video models these last few weeks! LTX Video is now in Diffusers with finetuning and structure-control support coming shortly. This model comes from the amazing brains at Lightricks 💫 🧑🍳 LTXV is very smol compared to some other open source models, but packs twice their punch! Fast generation, low memory requirements, high quality - what more do we need? Just two years ago, image generation models struggled at 2B param scale but now we have entirely different beasts 💪 Links in comment

If you're improving your LLM skills on real world use cases, this free course just got real! Smol course now has 4 chapters, and the most important was just released. 🌎 Chapter 4 shows you how to evaluate models on custom use cases. So you can test out the models you trained in the earlier chapters to see if they do the job. 📚 The course walks through using simple libraries to create an evaluation dataset for a custom domain. Libraries like lighteval, distilabel, and argilla. 🤯 If you've ever wondered how to evaluate an LLM for you problem, this is the material for you. We'll return to this chapter in a capstone project!

Hello Llama 3.2! 🗣️🦙 Build a Siri-like coding assistant that responds to "Hello Llama" in 100 lines of python! This is all possible with gradio-webrtc, the easiest way to add audio/video streaming to your AI models! Links to repo and Hugging Face space below:

[FineWeb2 - Annotation Sprint] It's amazing to see “language teams” growing every day! 🤗 Annotation can be tedious and requires a lot of focus, so it’s always easier—and way more fun—when done together. Some datasets already have over 15 contributors—👏—while others rely on just one amazing person (double 👏👏 for them!). Finding contributors for less widespread languages can be tricky! Here are a few tips to connect with your language community: 🦜 Call your community in your language: We’ve prepared templates you can translate before publishing on Social Media or email. 🪡 Make the task simpler for all: Translate the guidelines! They can be dense, and the examples are super helpful for getting it right. 🫚 Share the initiative widely with anyone passionate about supporting their language. The only requirement is fluency! And you, what are your tips? #fineWeb2 #argilla

✨ We just released an overview of the permissions for fine-grained tokens by hovering over the badge on Hugging Face token settings page (org and user). It will show the highest permission you've set for each entity