We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 48f3a8a commit c7466edCopy full SHA for c7466ed
README.md
@@ -37,7 +37,7 @@ python -m mlx_lm.fuse --model models/Qwen1.5-32B-Chat --save-path models/Qwen1.5
37
```
38
39
对合并后的模型进行量化加速:
40
-python convert_model.py
+python tools/compress_model.py
41
42
对微调训练后的模型进行对话测试:
43
python chat.py
tools/compress_model.py
@@ -3,7 +3,7 @@
3
# Compress Qwen1.5-32B-Chat.
4
convert(
5
"models/Qwen1.5-32B-Chat",
6
- mlx_path="mlx_model/Qwen1.5-32B-Chat",
+ mlx_path="models/Qwen1.5-32B-Chat-4Bit",
7
quantize=True
8
)
9
0 commit comments