Finetuning 24B Models with Poe.py

#1
by Naphula - opened
DarkArtsForge org

The training script has been uploaded here. It is very simple to recreate this finetune in less than 15 mins on runpod.

The gemma 4 kit works great for finetuning other archs such as mistral and is much more affordable than using axolotl serverless templates.

Make sure you use A100 with PyTorch v2.4.0, then run this (for Gemma 4 you probably need much higher epochs or LR than with Mistral).

pip install hf && \
hf download 26B-Suite/Gemma4-FinetuneKit gemma4_wheels.tar.gz --repo-type dataset --local-dir /workspace && \
tar -xzvf /workspace/gemma4_wheels.tar.gz -C /workspace && \
pip install --no-cache-dir --no-index --upgrade --find-links=/workspace/clean_wheels \
  torch torchvision torchaudio transformers peft trl accelerate bitsandbytes datasets sentencepiece protobuf huggingface_hub

export HF_TOKEN="hf_YourTokenHere"
hf download MuXodious/Cydonia-24B-v4.3-absolute-heresy --local-dir /workspace/MuXodious--Cydonia-24B-v4.3-absolute-heresy --token hf_YourTokenHere

python Poe.py

Sign up or log in to comment