Update README.md
Browse files
README.md
CHANGED
@@ -6,8 +6,8 @@ This project leverages the powerful LLaMA 2 7b language model to create an inter
|
|
6 |
## Prompt
|
7 |
Start the converstaion by saying, "Hello Krishna, " followed by your question.
|
8 |
|
9 |
-
## Try on your free colab!
|
10 |
-
-> Make sure that GPU is enabled under runtime settings.
|
11 |
First install libraries
|
12 |
```python
|
13 |
!pip install transformers accelerate bitsandbytes
|
|
|
6 |
## Prompt
|
7 |
Start the converstaion by saying, "Hello Krishna, " followed by your question.
|
8 |
|
9 |
+
## Try on your free colab using 4 bit- quantization!
|
10 |
+
-> We will make the model load in smaller bit precision which allow us to use free colab gpu. Make sure that GPU is enabled under runtime settings.
|
11 |
First install libraries
|
12 |
```python
|
13 |
!pip install transformers accelerate bitsandbytes
|