Pythia-70m supervised finetuned with Anthropic-hh-rlhf dataset for 1 epoch.
Benchmark evaluations included in repo done using lm-evaluation-harness.
See Pythia-70m for model details (paper).
Pythia-70m supervised finetuned with Anthropic-hh-rlhf dataset for 1 epoch.
Benchmark evaluations included in repo done using lm-evaluation-harness.
See Pythia-70m for model details (paper).