Update README.md
Browse files
README.md
CHANGED
|
@@ -11,6 +11,13 @@ This model is an int4 model with group_size 128 and symmetric quantization of [m
|
|
| 11 |
Please follow the license of the original model.
|
| 12 |
|
| 13 |
## INT4 Inference
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
```python
|
| 15 |
from transformers import AutoProcessor, Mistral3ForConditionalGeneration, AutoTokenizer
|
| 16 |
from huggingface_hub import hf_hub_download
|
|
|
|
| 11 |
Please follow the license of the original model.
|
| 12 |
|
| 13 |
## INT4 Inference
|
| 14 |
+
|
| 15 |
+
**Requirements**
|
| 16 |
+
~~~bash
|
| 17 |
+
pip install git+https://github.com/huggingface/transformers.git
|
| 18 |
+
~~~
|
| 19 |
+
**Note:** There is no official Hugging Face implementation of the original model. The following code may have issues.
|
| 20 |
+
|
| 21 |
```python
|
| 22 |
from transformers import AutoProcessor, Mistral3ForConditionalGeneration, AutoTokenizer
|
| 23 |
from huggingface_hub import hf_hub_download
|