Hugging Face's logo

izzcw
/
dpo_crafting_lora_from_base

PEFT
TensorBoard
Safetensors
llama-factory
lora
trl
dpo
Generated from Trainer
Model card Files Metrics Community
dpo_crafting_lora_from_base / runs
  • 1 contributor
 History: 3 commits
izzcw's picture
izzcw
Training in progress, step 1500
d526a30 verified