Hey Reachy Mini community! NVIDIA gave us a Golden Ticket to #NVIDIAGTC for you! Win the ultimate GTC experience (~$7k value), including ✅ GTC Conference pass 🤯 ✅ VIP seating at Jensen's keynote 🤯🤯 ✅ NVIDIA DGX Spark 🤯🤯🤯 The winner will have 1️⃣ published their

A few days back, following a long line of excellent proprietary models, Voyage AI by MongoDB released their 🚨 first ever open-weights embedding model for retrieval 🚨! It's called voyage-4-nano, it's multilingual, and very efficient. Details in 🧵

New TRL + OpenEnv example! 💥 Fine-tune an LLM to play Sudoku using an RL environment 🕹️ with OpenEnv Includes a script that runs on a single or multiple GPUs with vLLM, plus a Colab-ready notebook. Enjoy!

💥 `hf-mem` v0.4.1 now also estimates KV cache memory requirements for any context length and batch size with the `--experimental` flag! `uvx hf-mem --model-id ... --experimental` will automatically pull the required information from the Hugging Face Hub to include the KV cache

🤯 here is claude code building a landing page with vs without front-end design skill i made a crash course on agent skills (link below) 👇

From Anthropic's Claude Code best practices, and we couldn't agree more: "CLI tools are the most context-efficient way to interact with external services." That's why in 𝚑𝚞𝚐𝚐𝚒𝚗𝚐𝚏𝚊𝚌𝚎_𝚑𝚞𝚋 v1.4.0, we rebuilt the 𝚑𝚏 CLI as the go-to entry point to the Hub for AI

After nearly a year of development, 🤗 Transformers.js v4 Preview is finally out on npm! npm i @huggingface/transformers@next Build WebGPU-accelerated AI applications that run everywhere: browsers, Node.js, Bun, Deno, Electron, and more. See what's new in our blog post 👇

More embedding models and an even more reliable inference engine is what you get with Hugging Face Text Embeddings Inference v1.9.0 💥 More in the thread 🧵

What happens when you make an LLM drive a car where physics are real and actions can't be undone? I ported CARLA, the autonomous driving simulator, to OpenEnv and added training via TRL + HF Spaces In 50 steps, Qwen 0.6B learns to swerve and brake to avoid pedestrians

I broke my left thumb and I'll be trying Wispr Flow, , Monologue and Handy for daily workflows. Any recommendation?

🪣 We just shipped Storage Buckets: S3-like mutable storage, cheaper & faster Git falls short for everything on high-throughput side of AI (checkpoints, processed data, agent traces, logs etc) Buckets fixes that: fast writes, overwrites, directory sync 💨 All powered by Xet

Nemotron 3 Super by NVIDIA AI is here! NVIDIA's hybrid Mamba2/Transformer models are now natively supported in transformers (no trust_remote_code needed) Fine-tune them with TRL in just a few lines of code. Notebook + script included to get started right away. goooo!

Want to work at Hugging Face? We're hiring someone to work with us on bridging the gap between Hugging Face and our partners as AWS, GCP or Azure among others, through blogs, demos, talks, hands-on integrations, etc. Apply below if interested and ask us anything!

ML Apps were never that easy to build 🚀

Transformers.js monthly downloads 🤯📈 2023/03 ▏3.2K 2024/03 █ 266K 2025/03 ██ 764K 2026/03 ████████████ 4.4M Thanks so much to this amazing community! 🤗 We're excited to see what you build next!

x.com/i/article/2038…

Earlier this month, Apple introduced Simple Self-Distillation: a fine-tuning method that improves models on coding tasks just by sampling from the model and training on its own outputs with plain cross-entropy and… it's already supported in TRL, built by Kashif Rasul. you can really

Introducing ml-intern, the agent that just automated the post-training team Hugging Face It's an open-source implementation of the real research loop that our ML researchers do every day. You give it a prompt, it researches papers, goes through citations, implements ideas in GPU

Today we launch smol-audio A collection of notebooks & scripts to build on cutting-edge local audio models ⚡️ Already in the cookbook: > Fine-tune Whisper / Parakeet / Voxtral / Granite Speech > Fine-tune Audio Flamingo 3 (full + LoRA) > Dialogue TTS with Dia-1.6B > Zero-shot

x.com/i/article/2052…