423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-18 04:40:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

support quantization in export model

Browse Source 
Former-commit-id: f32500ae6edccab7d14df4c92467e15986866def
This commit is contained in:
hiyouga
2023-12-15 23:44:50 +08:00
parent ef730c23e2
commit a08089f449
9 changed files with 120 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
README_zh.md
View File

@@ -479,7 +479,10 @@ python src/export_model.py \
```
> [!WARNING]
> 尚不支持 GPTQ 量化模型的 LoRA 权重合并及导出。
> 尚不支持量化模型的 LoRA 权重合并及导出。
> [!TIP]
> 使用 `--export_quantization_bit 4` 和 `--export_quantization_dataset data/wiki_demo.txt` 量化导出模型。
### API 服务