Skip to content

bdytx5

ppo

Based on cleanrl/EleutherAI_pythia-1b-deduped__sft__tldr

Tags

  • safetensors
  • gpt_neox
  • generated_from_trainer
  • conversational
  • arxiv:1909.08593
  • base_model:cleanrl/EleutherAI_pythia-1b-deduped__sft__tldr
  • base_model:finetune:cleanrl/EleutherAI_pythia-1b-deduped__sft__tldr
  • text-generation-inference
  • endpoints_compatible
  • region:us
Author
bdytx5
Task
text-generation
Library
transformers
Architecture
gpt_neox
Base model
cleanrl/EleutherAI_pythia-1b-deduped__sft__tldr
Downloads
7
Likes
0
ppo — AI Model — AIMarketly