lomahony/pythia-2.8b-helpful-sft-epoch2
Text Generation
•
3B
•
Updated
•
7
pythia-helpful-epoch2
Pythia-2.8b supervised finetuned and DPO finetuned with the helpful subset of Anthropic-hh-rlhf dataset for a second epoch.
-
-
lomahony/pythia-1b-helpful-sft-epoch2
Text Generation • 1B • Updated • 1 -
lomahony/pythia-1.4b-helpful-sft-epoch2
Text Generation • 1B • Updated • 1 -
lomahony/pythia-410m-helpful-sft-epoch2
Text Generation • 0.4B • Updated • 1 -
lomahony/pythia-70m-helpful-sft-epoch2
Text Generation • 70.4M • Updated • 1 -
lomahony/pythia-160m-helpful-sft-epoch2
Text Generation • 0.2B • Updated • 6