CoMMET: A Psychologically Grounded Benchmark for Evaluating Theory of Mind in Multimodal LLMs Paper • 2603.11915 • Published 16 days ago • 1
Running on CPU Upgrade Featured 420 ML Intern 🤖 420 Notify users that ML Intern has moved to HuggingChat
view article Article Shipping a Trillion Parameters With a Hub Bucket: Delta Weight Sync in TRL +6 aminediroHF, qgallouedec, kashif, lewtun, edbeeching, albertvillanova, lvwerra, sergiopaniego • May 27 • 50
view article Article Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv sergiopaniego • Aug 5 • 27
Towards Robust Reinforcement Learning for Small-Scale Language Model Agents Paper • 2607.25091 • Published Jul 27 • 8
MaziyarPanahi/calme-3.2-instruct-78b Text Generation • 78B • Updated Jan 20, 2025 • 465 • 228
view article Article Be Ready Before the Attack: A Practical Guide to Self-Hosting an Open Model for Cyber Defense jeffboudier • Jul 20 • 20
view article Article Welcome Gemma 4: Frontier multimodal intelligence on device +5 merve, pcuenq, sergiopaniego, burtenshaw, Steveeeeeeen, alvarobartt, SaylorTwift • Apr 2 • 928