Update README.md
Browse files
README.md
CHANGED
|
@@ -38,6 +38,12 @@ You need to download the .gguf model first
|
|
| 38 |
pip install llama-cpp-python
|
| 39 |
```
|
| 40 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
```python
|
| 42 |
from llama_cpp import Llama
|
| 43 |
|
|
|
|
| 38 |
pip install llama-cpp-python
|
| 39 |
```
|
| 40 |
|
| 41 |
+
If you want to use the gpu instead
|
| 42 |
+
|
| 43 |
+
```python
|
| 44 |
+
CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python --force-reinstall --upgrade --no-cache-dir
|
| 45 |
+
```
|
| 46 |
+
|
| 47 |
```python
|
| 48 |
from llama_cpp import Llama
|
| 49 |
|