search

artidoro / qlora

QLoRA: Efficient Finetuning of Quantized LLMs
https://arxiv.org/abs/2305.14314
MIT License
10.08k stars 823 forks source link

Qlora Read me fix #272

Open Vezora-Corp opened 1 year ago

Vezora-Corp commented 1 year ago

The read me qlora template gets memory error with default optimizer. Using "--optim adamw_bnb_8bit" fixes the error as for quant models. Updated read me: README.md