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
197
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

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

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