Open rwl4 opened 4 months ago
We're working on it! Phi 3 medium support will most likely come out first and then small due to differing architecture.
@rwl4 Currrently we support phi-3 mini via https://colab.research.google.com/drive/1NvkBmkHfucGO3Ve9s1NKZvMNlw5p83ym?usp=sharing and https://huggingface.co/unsloth/Phi-3-mini-4k-instruct-bnb-4bit
any updates on this?
waiting for it! So thanks. :smile:
It's out!! @JackCloudman @joshib123 @rwl4
https://x.com/danielhanchen/status/1793762458437578955
Phi 3 medium and mini. Small will be supported later
@rwl4 @JackCloudman @joshib123 We support Phi-3 Medium and Mini now! See https://github.com/unslothai/unsloth/releases/tag/May-2024 (also includes Colabs)
Small is still in the works!
Please update Unsloth for local machines. For Colab or Kaggle just refresh and restart the env!
pip uninstall unsloth -y
pip install --upgrade --force-reinstall --no-cache-dir git+https://github.com/unslothai/unsloth.git
Hi @danielhanchen, thanks for the update. But, when I tried to finetune the Phi-3-medium the training loss goes from 1.80 to 0 after first step. Wondering if there is a bug somewhere in the code? PS: the same code worked for other models (such as Llama-3-8b).
@joshib123 I don't think there's a bug - that probably means ur learning rate is too high
@danielhanchen thanks for the impressive work! Any news on phi3 small?
@anakin87 No sorry - Small is a vastly different architecture :(
It would be great to see these models work!
Done. :)