Update README.md
Browse files
README.md
CHANGED
@@ -9,6 +9,8 @@ Recommended to hace over 10GB VRAM (Test Round consumes over 9GB VRAM).
|
|
9 |
# Pre-requirements
|
10 |
- transformers==4.46.2
|
11 |
- torch==2.5.1
|
|
|
|
|
12 |
## Single Chat
|
13 |
|
14 |
Here's how to load and use the quantized model:
|
|
|
9 |
# Pre-requirements
|
10 |
- transformers==4.46.2
|
11 |
- torch==2.5.1
|
12 |
+
- bitsandbytes
|
13 |
+
- accelerate
|
14 |
## Single Chat
|
15 |
|
16 |
Here's how to load and use the quantized model:
|