SynLogic Collection Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond • 5 items • Updated 4 days ago • 7
Step 1: Reproducing DeepSeek's Distilled Models Collection Code for training and evaluation: https://github.com/huggingface/open-r1 • 3 items • Updated 11 days ago • 2
Cosmos-Reason1 Collection Multimodal world understanding through reasoning • 5 items • Updated about 9 hours ago • 26
Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding Paper • 2505.22618 • Published 9 days ago • 39
xLAM-2 Collection A family of Large Action Model for multi-turn conversation and tool-use • 10 items • Updated May 5 • 16
SmolLM2 Collection State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 16 items • Updated May 5 • 266
AceReason Collection Math and Code reasoning model trained through reinforcement learning (RL) • 4 items • Updated about 9 hours ago • 6