CoolFace
Modelpublic

mxcui/sumgrad-imdb-ppo-prop0.2-alpha0.6-seed42-mean_kl0.1-gpt2

sourceHugging Faceupdated 3mo agoView on Hugging Face
0likes48downloads
4 commits on main
0be0c553mo ago

End of training

mxcui
c2703f93mo ago

Upload tokenizer

mxcui
0f93a1b3mo ago

Upload mxcui/sumgrad-imdb-ppo-prop0.2-alpha0.6-seed42-mean_kl0.1-gpt2 model weights

mxcui
65a929a3mo ago

initial commit

mxcui