Repos moved out of trl-lib: trainers TRL removed (DDPO, XPO, PRM) and early demos. Old trl-lib URLs redirect here.
AI & ML interests
None defined yet.
Recent Activity
models 8
trl-archive/Qwen2-0.5B-Reward-Math-Sheperd
Token Classification • 0.5B • Updated • 58 • 1
trl-archive/Qwen2-0.5B-XPO
Text Generation • 0.5B • Updated • 11
trl-archive/Qwen2-0.5B-DPO
Text Generation • 0.5B • Updated • 44 • 4
trl-archive/qwen1.5-0.5b-sft
Text Generation • 0.5B • Updated • 33
trl-archive/ddpo-aesthetic-predictor
Updated • 4
trl-archive/llama-7b-hh-rm-adapter
Updated • 2
trl-archive/llama-7b-se-rm-peft
Updated • 8
trl-archive/llama-7b-se-peft
Updated • 4
datasets 7
trl-archive/OpenMathReasoning
Viewer • Updated • 3.2M • 754
trl-archive/prm800k
Viewer • Updated • 41.2k • 227 • 7
trl-archive/math_shepherd
Viewer • Updated • 445k • 1.56k • 12
trl-archive/alpaca-cleaned
Viewer • Updated • 51.8k • 21
trl-archive/Capybara-Preferences
Viewer • Updated • 15.4k • 18
trl-archive/capybara-preferencces-7k
Viewer • Updated • 7.56k • 88
trl-archive/ultrachat_200k_chatml
Viewer • Updated • 231k • 54 • 3