Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
OpenDAS
Lmdeploy
Commits
43f75f75
Unverified
Commit
43f75f75
authored
Aug 14, 2023
by
AllentDan
Committed by
GitHub
Aug 14, 2023
Browse files
fix auto_awq readme (#228)
* fix auto_awq readme * hide w_sym option
parent
902a3e16
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
2 additions
and
1 deletion
+2
-1
README.md
README.md
+1
-1
README_zh-CN.md
README_zh-CN.md
+1
-0
No files found.
README.md
View file @
43f75f75
...
...
@@ -182,8 +182,8 @@ LMDeploy uses AWQ algorithm for model weight quantization
```
python3 -m lmdeploy.lite.apis.auto_awq \
--model $HF_MODEL \
--w_bits 4 \ # Bit number for weight quantization
--w_sym False \ # Whether to use symmetric quantization for weights
--w_group_size 128 \ # Group size for weight quantization statistics
--work_dir $WORK_DIR \ # Directory saving quantization parameters from Step 1
```
...
...
README_zh-CN.md
View file @
43f75f75
...
...
@@ -180,6 +180,7 @@ LMDeploy 使用 [AWQ](https://arxiv.org/abs/2306.00978) 算法对模型权重进
```
python3 -m lmdeploy.lite.apis.auto_awq \
--model $HF_MODEL \
--w_bits 4 \ # 权重量化的 bit 数
--w_group_size 128 \ # 权重量化分组统计尺寸
--work_dir $WORK_DIR \ # Step 1 保存量化参数的目录
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment