Update README.md
Browse files
README.md
CHANGED
|
@@ -7,7 +7,9 @@ base_model:
|
|
| 7 |
- HuggingFaceTB/SmolVLM-Instruct
|
| 8 |
---
|
| 9 |
|
| 10 |
-
4bit nf4 quantized version, you can find the quantized version generation code below
|
|
|
|
|
|
|
| 11 |
```
|
| 12 |
from transformers import BitsAndBytesConfig
|
| 13 |
|
|
|
|
| 7 |
- HuggingFaceTB/SmolVLM-Instruct
|
| 8 |
---
|
| 9 |
|
| 10 |
+
4bit nf4 quantized version, you can find the quantized version generation code below.
|
| 11 |
+
|
| 12 |
+
The 8bit config seems to be more accurate, when compared to this one.
|
| 13 |
```
|
| 14 |
from transformers import BitsAndBytesConfig
|
| 15 |
|