pythia-helpful-epoch2
Collection
Pythia-2.8b supervised finetuned and DPO finetuned with the helpful subset of Anthropic-hh-rlhf dataset for a second epoch.
•
6 items
•
Updated
No model card
- Downloads last month
- 0
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support