Reasoning models like o3 and o4-mini are advancing faster than ever, but imagine what will be possible when they can run locally in your browser! π€―
Well, with π€ Transformers.js, you can do just that! Here's Zyphra's new ZR1 model running at over 100 tokens/second on WebGPU! β‘οΈ
Giving models access to browser APIs (like File System, Screen Capture, and more) could unlock an entirely new class of web experiences that are personalized, interactive, and run locally in a secure, sandboxed environment.
Say hallo to GermaNER πͺβ a lightweight, high-accuracy NER model for German texts, powered by XLM-RoBERTa + LoRA adapters! β‘ Fast, efficient, and open-source β perfect for tagging names, places & orgs in real-world German data. Try it now on Hugging Face π fau/GermaNER
π Videoxity is live on Hugging Face! ποΈ A powerful, modular toolkit for intelligent video manipulation and scene editing.
With Videoxity, you can:
πΌοΈ Auto-caption keyframes with BLIP
π§ Filter scenes using natural language (e.g. βremove dog scenesβ)
βοΈ Seamlessly trim videos with FFmpeg
π Generate frame-based summaries
Powered by Groq LLM + LangChain, OpenCV, BLIP, and SentenceTransformers, Videoxity bridges vision and language to give developers full control over video content. π§ Built for developers. Feedback welcome!
Interact with your PDF documents like never before! π€― Extract text & images, then ask context-aware questions based on both. Powered by RAG techniques & multimodal LLMs. Perfect for studying, research & more! ππ Try it out now!!!! βοΈ