Update README.md
Browse files
README.md
CHANGED
@@ -109,6 +109,7 @@ pip install flash-attn --no-build-isolation
|
|
109 |
Then you could use our model:
|
110 |
```python
|
111 |
from transformers import AutoModel, AutoTokenizer
|
|
|
112 |
|
113 |
# model setting
|
114 |
model_path = 'OpenGVLab/VideoChat-Flash-Qwen2_5-2B_res448'
|
|
|
109 |
Then you could use our model:
|
110 |
```python
|
111 |
from transformers import AutoModel, AutoTokenizer
|
112 |
+
import torch
|
113 |
|
114 |
# model setting
|
115 |
model_path = 'OpenGVLab/VideoChat-Flash-Qwen2_5-2B_res448'
|