Lora fine-tuning parameters
#9
by
svippixel
- opened
Thank you for your efforts. Could you please provide the parameters for Lora fine-tuning? I would like to conduct an experiment locally based on this model to see the effects. I would greatly appreciate it.
That's entirely subjective, I suggest looking into axolotl examples.
lucyknada
changed discussion status to
closed
Axolotl examples : https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples
LLaMafactory examples for Lora : https://github.com/hiyouga/LLaMA-Factory/tree/main/examples/train_lora