mxcui/sumgrad-imdb-ppo-prop0.2-alpha0.6-seed42-mean_kl0.1-gpt2
048
End of training
Upload tokenizer
Upload mxcui/sumgrad-imdb-ppo-prop0.2-alpha0.6-seed42-mean_kl0.1-gpt2 model weights
initial commit
End of training
Upload tokenizer
Upload mxcui/sumgrad-imdb-ppo-prop0.2-alpha0.6-seed42-mean_kl0.1-gpt2 model weights
initial commit