Update README.md
Browse files
README.md
CHANGED
|
@@ -29,7 +29,9 @@ AMD-Quark has been installed from source code inside the Docker image `rocm/vllm
|
|
| 29 |
|
| 30 |
**Quantization scripts:**
|
| 31 |
|
| 32 |
-
-
|
|
|
|
|
|
|
| 33 |
```
|
| 34 |
import runpy
|
| 35 |
from quark.torch import LLMTemplate
|
|
|
|
| 29 |
|
| 30 |
**Quantization scripts:**
|
| 31 |
|
| 32 |
+
Note that GLM-4.7 is not in the built-in model template list in Quark V0.11, it has to be registered before quantization.
|
| 33 |
+
|
| 34 |
+
- **Step1:** Register new template: creat fle `Quark/examples/torch/language_modeling/llm_ptq/quantize_glm.py`
|
| 35 |
```
|
| 36 |
import runpy
|
| 37 |
from quark.torch import LLMTemplate
|