添加XPU(Intel-GPU)支持
修改API默认使用llama.cpp默认值
安装显卡驱动
"C:\Program Files (x86)\Intel\oneAPI\pytorch-gpu-dev-0.5\oneapi-vars.bat"
"C:\Program Files (x86)\Intel\oneAPI\ocloc\2024.2\env\vars.bat"
预览版
pip3 install torch --index-url https://download.pytorch.org/whl/test/xpu
夜间版
pip3 install --pre torch --index-url https://download.pytorch.org/whl/nightly/xpu
pip install -r requirements.txt
call "C:\Program Files (x86)\Intel\oneAPI\pytorch-gpu-dev-0.5\oneapi-vars.bat"
call "C:\Program Files (x86)\Intel\oneAPI\ocloc\2024.2\env\vars.bat"
python YakuYaku.py
台版轻小说翻译模型(large)v1.0(日本語 → 繁體中文)
A better practice on the same dataset produced by @SakuraUmi
Run server.py
in SakuraLLM/Sakura-13B-Galgame
python server.py \
--listen "127.0.0.1:5000" \
--model_name_or_path "SakuraLLM/Sakura-13B-LNovel-v0.8" \
--trust_remote_code \
--model_version 0.8 \
--use_gptq_model \
--no-auth