Open nyeeldzn opened 1 month ago
Thank you for that. Llama3.2 is similar to Llama3 or Llama3.1, so I support it in the newest code. You can try it by following these steps.
python finetune.py --model_type llama3 --data "data/train/alpaca_tiny.json" --model_path "LLMs/llama3/llama3.2-3B-Instruct" --adapter "lo
ra" --output_dir "output/llama3" --disable_wandb
Is there any expectation for compatibility with the newly released LLAMA3.2? As a developer I could help with the project?