AndroidLab
AndroidLab: First ever systematic benchmark for Android mobile agents shows that small, fine-tuned open models can power a JARVIS system on your smartphone 📱🔥
Aymeric Roucher 👨💻
I'm Aymeric ("m-ric"), Machine Learning Engineer at Hugging Face.
Latest posts
Anthropic Contextual RAG
Anthropic just released a chunk improvement technique that vastly improves RAG performance! 🔥
Aya Expanse
🌟 Cohere releases Aya 8B & 32B: SOTA multilingual models for 23 languages.
Blog post for Claude 3 5 Sonnet
Categories: 🤖 Agents Complete: Terminé Key insights: Claude-3.5-Sonnet is really strong on agentic behaviour, much stronger than GPT-4o. Publication: 2024/10/22 Rating: ⭐️⭐️ Read: 2024/10/22
CLEAR
🧠 CLEAR: first multimodal benchmark to make models forget what we want them to forget
Colbert vs rerankers
How to re-rank your snippets in RAG ⇒ ColBERT vs Rerankers vs Cross-Encoders ⚔️
Draghi report
image.png
Easier tool building arrives in transformers agent
Transformers v4.45.0 released: includes a lightning-fast method to build tools! ⚡️
Farmer Chat blog post
🤗 I’m very proud to have supported CGIAR and Digital Green in making Farmer.chat, an app that supports 20k smallholder farmers on a daily basis 🌾
Hunyuan-Large
🚀 Hunyuan-Large just released by Tencent: Largest ever open MoE LLM, only 52B active parameters but beats LLaMA 3.1-405B on most academic benchmarks