Update README.md
Browse files
README.md
CHANGED
@@ -52,14 +52,16 @@ llama-server -m base_model.gguf --lora html-model-tinyllama-chat-bnb-4bit-f32.gg
|
|
52 |
|
53 |
|
54 |
## Use python script
|
|
|
55 |
```bash
|
56 |
pip install llama-cpp-python
|
57 |
```
|
|
|
58 |
```python
|
59 |
from llama_cpp import Llama
|
60 |
|
61 |
# Replace with the actual path to your downloaded GGUF file
|
62 |
-
model_path = "/path/to/your/downloaded/html-model-tinyllama-chat-bnb-4bit-F32-GGUF"
|
63 |
|
64 |
llm = Llama(model_path=model_path)
|
65 |
|
|
|
52 |
|
53 |
|
54 |
## Use python script
|
55 |
+
### Install llama.cpp
|
56 |
```bash
|
57 |
pip install llama-cpp-python
|
58 |
```
|
59 |
+
### Python script to run the model
|
60 |
```python
|
61 |
from llama_cpp import Llama
|
62 |
|
63 |
# Replace with the actual path to your downloaded GGUF file
|
64 |
+
model_path = "/path/to/your/downloaded/html-model-tinyllama-chat-bnb-4bit-F32-GGUF.gguf"
|
65 |
|
66 |
llm = Llama(model_path=model_path)
|
67 |
|