Pythia-160m supervised finetuned with Anthropic-hh-rlhf dataset for 1 epoch.

wandb log

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

See Pythia-160m for model details (paper).

Downloads last month: 189

Safetensors

Model size

213M params

Tensor type

F32

BOOL

Inference Providers NEW

Text Generation

This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Dataset used to train lomahony/eleuther-pythia160m-hh-sft

Collection including lomahony/eleuther-pythia160m-hh-sft

Pythia-hh-all-sft-dpo

Collection

Pythia models supervised finetuned and DPO finetuned with all of Anthropic-hh-rlhf dataset for 1 epoch. • 13 items • Updated Mar 12, 2024