jiaxwang commited on
Commit
c16df18
·
verified ·
1 Parent(s): 526f038

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -29,7 +29,7 @@ AMD-Quark has been installed from source code inside the Docker image `rocm/vllm
29
 
30
  **Quantization scripts:**
31
 
32
- Step1: Creat the quantize_glm.py
33
  ```
34
  import runpy
35
  from quark.torch import LLMTemplate
@@ -50,7 +50,7 @@ quantize_script = "/app/Quark/examples/torch/language_modeling/llm_ptq/quantize_
50
 
51
  runpy.run_path(quantize_script, run_name="__main__")
52
  ```
53
- Step1: Quantize with the quantize_glm.py
54
  ```
55
  export CUDA_VISIBLE_DEVICES=0,1,2,3
56
  export MODEL_DIR=zai-org/GLM-4.7
 
29
 
30
  **Quantization scripts:**
31
 
32
+ - **Step1:** Creat the quantize_glm.py
33
  ```
34
  import runpy
35
  from quark.torch import LLMTemplate
 
50
 
51
  runpy.run_path(quantize_script, run_name="__main__")
52
  ```
53
+ - **Step2:** Quantize with the quantize_glm.py
54
  ```
55
  export CUDA_VISIBLE_DEVICES=0,1,2,3
56
  export MODEL_DIR=zai-org/GLM-4.7