arielnlee / Platypus

Code for fine-tuning Platypus fam LLMs using LoRA

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Fine tuning Script for OpenOrca-Platypus2-13B

virentakia opened this issue · comments

Amazing work - so good to see an effective 13b model.

Question - Can this model (Platypus2-13B) be further fine-tuned on a custom dataset?

  • Is there a fine-tuning script that can be referred to?
  • Should the data set be formatted, as per the training dataset to fine-tune the model?
  • Any other tips/guides to further fine-tune this?