m_ric
@AymericRoucher
Building Agents at Hugging Face 🤗
And that's when I met the one and only @AndrewYNg, whose melodious voice first introduced me to the green pastures of machine learning, as I began my journey 5 years back: it means a lot! ✨ I'm thrilled about this new course! You'll learn to use smolagents and build agents that…
New short course: Building Code Agents with Hugging Face smolagents! Learn how to build code agents in this course, created in collaboration with @huggingface, and taught by @Thom_Wolf, its co-founder and CSO, and @AymericRoucher, Hugging Face’s Project Lead on Agents.…
Great insights by Manus team on engineering SOTA agents: - KV cache is king in agents - filesystem is a great mechanism for memory - keep errors in the trace - and more Read this !
After four overhauls and millions of real-world sessions, here are the lessons we learned about context engineering for AI agents: manus.im/blog/Context-E…
This is probably the last time in human history that an AI is outperformed by a real human coder. OpenAI achieved second place, completely autonomously.
1/N Yesterday in Tokyo we @OpenAI ran a 10‑hour live Humans vs AI exhibition at the AtCoder World Tour Finals Heuristic. We pointed an OpenAI reasoning model at the same brutal problem the finalists tackled—no human help, same rules, same clock. Buckle up. 👇
Recent WebSailor paper by Alibaba-NLP, shows how to post-train models for Deep Research - good insights in there, about creating a dataset then training recipe. I particularly like how the agentic RL at the end of post-training improves scores by ~4 p.p. across the board: RL +…
Reminder: SmolLM3 comes with built-in tool-calling, and it works really well!
Maybe FlashAttention is not that useful when you have MLP GEMMs that eat so much latency? Interesting graph in the latest blog post from @gpus_go_brrr!
Reachy Mini is out! 🐣 For 300$, you get a the perfect platform to experiment with robotics. I have little brothers who i've wanted to introduce to code forever, I can't wait to show them how to program their Reachy! Congrats @Thom_Wolf, @pollenrobotics and @huggingface 👏
Qwen left a hole in the Pareto frontier of optimal performance for a given size... So we just filled it: introducing 🔥 SmolLM3-3B 🔥 I helped the SmolLM team on the "make it agentic" part, by post-training the model on agent traces with @akseljoonas: the model is now also on…
Introducing SmolLM3: a strong, smol reasoner! > SoTA 3B model > dual mode reasoning (think/no_think) > long context, up to 128k > multilingual: en, fr, es, de, it, pt > fully open source (data, code, recipes) huggingface.co/blog/smollm3
Ever seen sheet music for choreographies? Turns out it's quite hard to note the minute precision of ballet movements. There are several systems of notation, from the oldest Beauchamp-Feuillet below to the modern Labanotation. A deep rabbit hole worth diving into! (sorry no…
Holy... `transformers` reached 1B downloads 😭 thanks everyone for making this possible, what an amazing community