cpatonn commited on
Commit
c2925c8
·
verified ·
1 Parent(s): eff2e78

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -14,7 +14,7 @@ base_model: zai-org/GLM-4.6V
14
 
15
  ### Quantization Details
16
 
17
- - **Quantization Method:** AWQ
18
  - **Bits:** 8
19
  - **Group Size:** 32
20
  - **Calibration Dataset:** [5CD-AI/LLaVA-CoT-o1-Instruct](https://huggingface.co/datasets/5CD-AI/LLaVA-CoT-o1-Instruct)
@@ -45,6 +45,10 @@ vllm serve cyankiwi/GLM-4.6V-AWQ-8bit
45
 
46
  ## Additional Information
47
 
 
 
 
 
48
  ### Changelog
49
 
50
  - **v1.0.0** - Initial quantized release
 
14
 
15
  ### Quantization Details
16
 
17
+ - **Quantization Method:** cyankiwi AWQ v1.0
18
  - **Bits:** 8
19
  - **Group Size:** 32
20
  - **Calibration Dataset:** [5CD-AI/LLaVA-CoT-o1-Instruct](https://huggingface.co/datasets/5CD-AI/LLaVA-CoT-o1-Instruct)
 
45
 
46
  ## Additional Information
47
 
48
+ ### Known Issues
49
+
50
+ - `tensor-parallel-size > 2` requires `--enable-expert-parallel`
51
+
52
  ### Changelog
53
 
54
  - **v1.0.0** - Initial quantized release