6
stars
5
commits
1
linked in READMEs
Mar 15, 2025
updated
arxiv.org/abs/2502.14669
4 commits
1 commits
homebrewltd/Maze-Reasoning-GRPO-v0.1
11
homebrewltd/Maze-Reasoning-Reset-v0.1
4
jan-hq/Maze-Reasoning
20
homebrewltd/Maze-Bench-v0.2
HuggingFaceH4/Magpie-Pro-DPO-100K-v0.1-Prompts
HuggingFaceH4/cai-conversation
HuggingFaceH4/spin-ultrachat-prompts-qwen-1.5-0.5b-iter0-iter1
2
HuggingFaceH4/h4-tests-format-dpo-dataset
0
janhq/visual-thinker
189