lomahony
/

eleuther-pythia12b-hh-dpo

Text Generation

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Edit model card

Pythia-12b supervised finetuned with Anthropic-hh-rlhf dataset for 1 epoch (sft-model), before DPO (paper) with same dataset for 1 epoch.

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

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

Downloads last month: 3

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

Collection including lomahony/eleuther-pythia12b-hh-dpo

Pythia-hh-all-sft-dpo

Pythia models supervised finetuned and DPO finetuned with all of Anthropic-hh-rlhf dataset for 1 epoch. • 13 items • Updated Mar 12