Commit
•
cf2e128
1
Parent(s):
5a78a9b
Updated to reflect changes in pr #3
Browse files
README.md
CHANGED
|
@@ -181,9 +181,10 @@ Please see the Responsible Use Guide available at https://ai.meta.com/llama/resp
|
|
| 181 |
## How to use this GPTQ model from Python code
|
| 182 |
|
| 183 |
To run the GPTQ version you first need to install transformers, peft, accelerate optimum and auto-gptq
|
|
|
|
| 184 |
pip install -q -U transformers peft accelerate optimum
|
| 185 |
-
|
| 186 |
pip install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu117/
|
|
|
|
| 187 |
|
| 188 |
Then you can run the model with:
|
| 189 |
|
|
|
|
| 181 |
## How to use this GPTQ model from Python code
|
| 182 |
|
| 183 |
To run the GPTQ version you first need to install transformers, peft, accelerate optimum and auto-gptq
|
| 184 |
+
```bash
|
| 185 |
pip install -q -U transformers peft accelerate optimum
|
|
|
|
| 186 |
pip install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu117/
|
| 187 |
+
```
|
| 188 |
|
| 189 |
Then you can run the model with:
|
| 190 |
|