view article Article Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face +3 abidlabs, znation, nouamanetazi, sasha, qgallouedec • Jul 29, 2025 • 230
(Some) Emergent Misalignment from Reward Hacking in RL Collection Model checkpoints from the project "(Some) Natural Emergent Misalignment from Reward Hacking in Non-Production RL" • 228 items • Updated Jul 1 • 7
view article Article How to generate text: using different decoding methods for language generation with Transformers patrickvonplaten • Mar 1, 2020 • 310
view article Article GGML and llama.cpp join HF to ensure the long-term progress of Local AI +4 ggerganov, ngxson, allozaur, lysandre, victor, julien-c • Feb 20 • 512
Gemma Scope Release Collection A comprehensive, open suite of sparse autoencoders for Gemma 2 2B and 9B. • 10 items • Updated Jul 21 • 24
RM Sycophancy (LLaMa) Collection https://alignment.anthropic.com/2025/auditing-mo-replication/ • 9 items • Updated Feb 15 • 3
Llama 2 Family Collection This collection hosts the transformers and original repos of the Llama 2 and Llama Guard releases • 13 items • Updated Dec 6, 2024 • 100
Beyond Transcription: Mechanistic Interpretability in ASR Paper • 2508.15882 • Published Aug 21, 2025 • 92
Intern-S1: A Scientific Multimodal Foundation Model Paper • 2508.15763 • Published Aug 21, 2025 • 275
Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens Paper • 2508.01191 • Published Aug 2, 2025 • 240
LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos Paper • 2508.14041 • Published Aug 19, 2025 • 59
🔍 Interpretability & Analysis of LMs Collection Outstanding research in LM interpretability and evaluation, summarized • 136 items • Updated May 26 • 120
Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 Paper • 2408.05147 • Published Aug 9, 2024 • 42
The Well Collection A 15TB collection of physics simulation datasets. • 18 items • Updated Mar 24, 2025 • 54
view article Article Learn the Hugging Face Kernel Hub in 5 Minutes +5 drbh, danieldk, Narsil, pcuenq, pagezyhf, merve, reach-vb • Jun 12, 2025 • 167
INTELLECT-2: A Reasoning Model Trained Through Globally Decentralized Reinforcement Learning Paper • 2505.07291 • Published May 12, 2025 • 16