amokrov commited on
Commit
4b9e271
·
verified ·
1 Parent(s): 7e1dc3b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ This is [Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) model converted to the
15
 
16
  ## Quantization Parameters
17
 
18
- Weight compression was performed using `nncf.compress_weights` with the following parameters:
19
 
20
  * mode: **INT4_ASYM**
21
  * ratio: **1.0**
 
15
 
16
  ## Quantization Parameters
17
 
18
+ The quantization was performed using `optimum-cli export openvino` with the following parameters:
19
 
20
  * mode: **INT4_ASYM**
21
  * ratio: **1.0**