Video-Text-to-Text
Transformers
Safetensors
English
Chinese
moss_vl
feature-extraction
Realtime
Streaming
Video-Understanding
Image-Understanding
MOSS-VL
OpenMOSS
multimodal
video
vision-language
custom_code
Instructions to use OpenMOSS-Team/MOSS-VL-Realtime with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMOSS-Team/MOSS-VL-Realtime with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpenMOSS-Team/MOSS-VL-Realtime", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
revert: preprocessor_config.json to stock (interpolation field was a no-op)
Browse filesThe interpolation field is not read by the framework
(valid kwarg name is resample; the parent class already defaults to BICUBIC and
the base _further_process_kwargs converts resample -> interpolation before
calling _preprocess). Verified bitwise-identical pixel_values with/without it.
- preprocessor_config.json +1 -2
preprocessor_config.json
CHANGED
|
@@ -22,6 +22,5 @@
|
|
| 22 |
0.5
|
| 23 |
],
|
| 24 |
"processor_class": "MossVLProcessor",
|
| 25 |
-
"image_processor_type": "MossVLImageProcessorFast"
|
| 26 |
-
"interpolation": "BICUBIC"
|
| 27 |
}
|
|
|
|
| 22 |
0.5
|
| 23 |
],
|
| 24 |
"processor_class": "MossVLProcessor",
|
| 25 |
+
"image_processor_type": "MossVLImageProcessorFast"
|
|
|
|
| 26 |
}
|