Working on an Infinite Craft-inspired card game with a friend. What do you guys think ?

📈 Scale open models with Hugging Face Text Generation Inference! 🚀 Customize with LoRA adapters ⚙️ Optimize with PEFT and TRL ☁️ Deploy on Google Cloud Platform with ease 🤖 Watch the demo from #GemmaDeveloperDay Tokyo → goo.gle/41bzOHe

You have no excuse with the new Data Studio in Hugging Face. It's easier than ever to explore your datasets, no need to be a Data Engineer. Here I ask an AI assistant to check DeepSeek-generated reasoning data for multiple </think> mentions, directly from HF

✨NEW in Hugging Face Datasets v3.3 🔥 Process datasets using async functions in .map() ! Crazy useful to use AI models like R1 from DeepSeek ...maybe to fine-tune smaller models later ? Screenshot of the full colab in comments

Almost 100k student in the Hugging Face agent course 🤯🤯🤯

🥊 Epic Agent Framework Showdown! Available today! 🔵 In the blue corner, as challenger, the experienced knowledge retriever: LlamaIndex 🦙 🛑 In the red corner, the defender, weighing in with lightweight efficiency: Hugging Face smolagents! 🔗 URL: huggingface.co/agents-course

The Hugging Face Agents Course now includes three major agent frameworks. LlamaIndex, LangChain, and our very own smolagents. We've worked to integrate the three frameworks in distinctive ways so that learners can reflect on when and where to use each. This also means that you

Final Unit of the Hugging Face agent course. Earn a certificate by challenging your agent skills on a subset of GAIA benchmark. 🎓

ヨーロッパ発LLM ProviderであるMistral AIから最新リリース×日本企業での活用法をライブデモで紹介してくれることになりました💻 LLM Providerが続々と日本のAI市場を意識されている流れは興味深いです Joffrey Thomas Mistral AI fullyconnected.jp #mistral

NEW: Mistral AI releases Mistral 3, a family of multimodal models, including three start-of-the-art dense models (3B, 8B, and 14B) and Mistral Large 3 (675B, 41B active). All Apache 2.0! 🤗 Surprisingly, the 3B is small enough to run 100% locally in your browser on WebGPU! 🤯