·
AI & ML interests
NLP, RL
Organizations
Illustrating Reinforcement Learning from Human Feedback (RLHF)
Viewer • Updated • 12.5k • 35
Viewer • Updated • 361k • 31
Dahoas/aimo-validation-aime
Viewer • Updated • 90 • 71
Dahoas/qwen-1.5-4B-default-positives-epoch-1-100
Viewer • Updated • 290k • 17
Dahoas/qwen-1.5-4B-tree-positives-epoch-2-100
Viewer • Updated • 491k • 37
Dahoas/qwen-1.5-4B-tree-positives-epoch-1-100
Viewer • Updated • 477k • 18
Dahoas/qwen-1.5-4B-epoch-1-test-100
Viewer • Updated • 498k • 11
Dahoas/qwen-1.5-4B-K-100-test
Viewer • Updated • 500k • 5
Dahoas/MATH_train_K_100_qwen_1.5_4B_outputs
Viewer • Updated • 750k • 32
Viewer • Updated • 750k • 27
• 2