trl-archive/llama-7b-se-peft

Updated Apr 6, 2023 • 4

Note StackLLaMA SFT adapter

trl-lib/llama-7b-se-rl-peft

Updated Apr 14, 2023 • 103

Note StackLLaMA RL adapter. Stays in trl-lib because it has a DOI

trl-archive/llama-7b-se-rm-peft

Updated Apr 6, 2023 • 8

Note StackLLaMA reward model adapter

trl-archive/llama-7b-hh-rm-adapter

Updated May 17, 2023 • 2

Note HH reward model adapter

trl-archive/ddpo-aesthetic-predictor

Updated Aug 18, 2023 • 4

Note DDPO, removed from TRL

trl-archive/Qwen2-0.5B-XPO

Text Generation • 0.5B • Updated Oct 24, 2024 • 11

Note XPO, removed from TRL

trl-archive/Qwen2-0.5B-Reward-Math-Sheperd

Token Classification • 0.5B • Updated Dec 9, 2024 • 54 • 1

Note Process reward model, PRM trainer removed from TRL

Note Stepwise supervision, PRM trainer removed from TRL

Note Stepwise supervision, PRM trainer removed from TRL

trl-archive/Qwen2-0.5B-DPO

Text Generation • 0.5B • Updated Sep 27, 2024 • 44 • 4

Note Early DPO demo

trl-archive/qwen1.5-0.5b-sft

Text Generation • 0.5B • Updated Mar 13, 2024 • 33

Note Early SFT demo

Note Early demo

Note Early demo

Note Early demo

Note Early demo

Note Early demo