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
1
models
42
lomahony/pythia-2.8b-helpful-sfted1-dpo-3epochs
Updated
lomahony/pythia-2.8b-helpful-sfted0-dpo-3epochs
Updated
lomahony/pythia-2.8b-helpful-sfted3-dpo-3epochs
Updated
lomahony/pythia-2.8b-helpful-sfted2-dpo-3epochs
Updated
lomahony/pythia-2.8b-helpful-sfted2-dpo-3epochs-old
Updated
lomahony/pythia-2.8b-helpful-sfted1-dpo-3epochs-old
Text Generation
•
Updated
•
3
lomahony/pythia-2.8b-helpful-sfted0-dpo-3epochs-old
Updated
lomahony/pythia-2.8b-helpful-sft-3epochs
Text Generation
•
Updated
•
4
lomahony/pythia-1.4b-helpful-sfted1-ppo-3epochs-old
Text Generation
•
Updated
•
3
lomahony/pythia-2.8b-helpful-sft-3epochs-old
Text Generation
•
Updated
•
2
datasets
None public yet