Wenboz
/

phi3-offline-dpo-lora-noise-0.0-5e-7-thre-1.5-42

alignment-handbook

Generated from Trainer

Model card Files Files and versions Community

phi3-offline-dpo-lora-noise-0.0-5e-7-thre-1.5-42 / tokenizer.json

Commit History

Training in progress, step 100

718f840
verified

Wenboz commited on Jul 9