Fine tune llama38b using touchtune
#84
by
realdanielbyrne
- opened
Fine-tuning Llama3-8B in torchtune, https://github.com/pytorch/torchtune
Torchtune provides LoRA, QLoRA, and full fine-tuning recipes for fine-tuning Llama3-8B on one or more GPUs.
Fine-tuning recipes
torchtune provides the following fine-tuning recipes.
| Training | Fine-tuning Method |
|---|---|
| Distributed Training [1 to 8 GPUs] | Full [code, example], LoRA [code, example] |
| Single Device / Low Memory [1 GPU] | Full [code, example], LoRA + QLoRA [code, example] |
| Single Device [1 GPU] | DPO [code, example] |
The basic command for a single-device LoRA fine-tune is
tune run lora_finetune_single_device --config llama3/8B_lora_single_device