EleutherAI_pythia-2.8b-deduped__ppo__tldr / model-00001-of-00002.safetensors

Commit History

Add vwxyzjn/EleutherAI_pythia-2.8b-deduped__ppo_left_padding_new_nowhiten_reward__tldr-ppo_left_padding_new_nowhiten_reward__77713__1710356835 checkpoint
905f2fb
verified

vwxyzjn commited on