Edit model card

Pythia-12b supervised finetuned with Anthropic-hh-rlhf dataset for 1 epoch.

wandb log

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

See Pythia-12b for model details (paper).

Downloads last month
2

Dataset used to train lomahony/eleuther-pythia12b-hh-sft0

Collection including lomahony/eleuther-pythia12b-hh-sft0