Edit model card

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).

Downloads last month
12

Dataset used to train lomahony/eleuther-pythia2.8b-hh-sft

Collection including lomahony/eleuther-pythia2.8b-hh-sft