665 B
665 B
language, tags, license, datasets
| language | tags | license | datasets | |||||
|---|---|---|---|---|---|---|---|---|
|
|
apache-2.0 |
|
Pythia-410m supervised finetuned with Anthropic-hh-rlhf dataset for 1 epoch.
Benchmark evaluations included in repo done using lm-evaluation-harness.
See Pythia-410m for model details (paper).