acwkim/ppo-humor
Reinforcement Learning • Updated
Cheol Woo Kim
acwkim
·
AI & ML interests
None yet
Recent Activity
updated a dataset 21 days ago
acwkim/mod-alg2 updated a dataset 22 days ago
acwkim/mod-alg2 published a dataset 2 months ago
acwkim/mod-alg2Organizations
models 10
acwkim/ppo-helpful
Reinforcement Learning • Updated
acwkim/ppo-harmless
Reinforcement Learning • Updated
acwkim/llama2-7b-assistant-sft-3
7B • Updated
acwkim/llama2-7b-3d-sft_2
7B • Updated
acwkim/mod-ppo-checkpoints
Updated
acwkim/llama2-7b-3d-sft
7B • Updated
acwkim/llama2-7b-hh-rlhf-sft
Updated • 1
acwkim/mod-dpo-safer
Updated • 29
acwkim/mod-dpo-better
Updated • 30