Skip to content

ammarik/llama3_finetuning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 

Repository files navigation

Fine-tuning of Llama 3.1 using QLoRA.

Based on Maxime Labonne's tutorial Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth, thank you.

Environment setup

conda create --name unsloth_env_1 python=3.11 pytorch-cuda=12.1 cudatoolkit notebook -c pytorch -c nvidia -y

About

Llama3 Finetuning

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published