Video-Text-to-Text
Transformers
Safetensors
English
qwen2
feature-extraction
multimodal
custom_code
Eval Results (legacy)
text-generation-inference
Instructions to use OpenGVLab/VideoChat-Flash-Qwen2_5-7B-1M_res224 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenGVLab/VideoChat-Flash-Qwen2_5-7B-1M_res224 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("OpenGVLab/VideoChat-Flash-Qwen2_5-7B-1M_res224", trust_remote_code=True) model = AutoModel.from_pretrained("OpenGVLab/VideoChat-Flash-Qwen2_5-7B-1M_res224", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -102,6 +102,7 @@ pip install av
|
|
| 102 |
pip install imageio
|
| 103 |
pip install decord
|
| 104 |
pip install opencv-python
|
|
|
|
| 105 |
pip install flash-attn --no-build-isolation
|
| 106 |
```
|
| 107 |
Then you could use our model:
|
|
|
|
| 102 |
pip install imageio
|
| 103 |
pip install decord
|
| 104 |
pip install opencv-python
|
| 105 |
+
# optional
|
| 106 |
pip install flash-attn --no-build-isolation
|
| 107 |
```
|
| 108 |
Then you could use our model:
|