RichardErkhov/lomahony_-_eleuther-pythia410m-hh-dpo-awq

Quantization made by Richard Erkhov.

Github

Discord

Request more models

eleuther-pythia410m-hh-dpo - AWQ

• Model creator: https://huggingface.co/lomahony/
• Original model: https://huggingface.co/lomahony/eleuther-pythia410m-hh-dpo/

Original model description:

language: - en tags: - pytorch - causal-lm - pythia license: apache-2.0 datasets: - Anthropic/hh-rlhf

Pythia-410m supervised finetuned with Anthropic-hh-rlhf dataset for 1 epoch (sft-model), before DPO (paper) with same dataset for 1 epoch.

wandb log

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

See Pythia-410m for original model details (paper).