language, tags, license, datasets

language	tags	license	datasets
en	pytorch causal-lm pythia	apache-2.0	Anthropic/hh-rlhf

Pythia-2.8b supervised finetuned with Anthropic-hh-rlhf dataset for 1 epoch.

wandb log

Benchmark evaluations included in repo done using lm-evaluation-harness.

See Pythia-2.8b for model details (paper).