tatsu-lab/alpaca
Viewer • Updated • 52k • 107k • 964
This model is a finetuned version of google/gemma-2b
More information needed
More information needed
This model was trained using the torchtune library using the following command:
/Users/salmanmohammadi/projects/torchtune/recipes/lora_finetune_single_device.py --config /Users/salmanmohammadi/projects/torchtune/recipes/configs/gemma/2B_lora_single_device.yaml \
device=mps \
epochs=1 \
max_steps_per_epoch=10
Base model
google/gemma-2b