Pythia models supervised finetuned and DPO finetuned with all of Anthropic-hh-rlhf dataset for 1 epoch.
Laura O'Mahony
lomahony
AI & ML interests
PhD student
Organizations
None yet
Collections
4
Papers
2
models
42
lomahony/pythia-410m-helpful-sft
Text Generation
•
Updated
•
1
lomahony/pythia-70m-helpful-sft
Text Generation
•
Updated
•
6
lomahony/pythia-1b-helpful-sft
Text Generation
•
Updated
•
5
lomahony/pythia-160m-helpful-sft
Text Generation
•
Updated
•
2
lomahony/pythia-1b-helpful-dpo
Text Generation
•
Updated
lomahony/pythia-70m-helpful-dpo
Text Generation
•
Updated
•
1
lomahony/pythia-160m-helpful-dpo
Text Generation
•
Updated
•
1
lomahony/pythia-1.4b-helpful-dpo
Text Generation
•
Updated
•
1
lomahony/pythia-2.8b-helpful-dpo
Text Generation
•
Updated
lomahony/pythia-1.4b-helpful-sft
Text Generation
•
Updated
datasets
None public yet