120a0035ac
* During the evaluation stage, Baichuan2 will raise type mismatch when training with bfloat16. Fix this issue by modifying modeling_baichuan.py. Add doc about how to modify this file. |
||
|---|---|---|
| .. | ||
| alpaca-qlora | ||
| simple-example | ||
| trl-example | ||
| README.md | ||
QLoRA Finetuning with IPEX-LLM
We provide Alpaca-QLoRA example, which ports Alpaca-LoRA to IPEX-LLM (using QLoRA algorithm) on Intel GPU.
Meanwhile, we also provide a simple example to help you get started with QLoRA Finetuning using IPEX-LLM, and TRL example to help you get started with QLoRA Finetuning using IPEX-LLM and TRL library.