Instructions to use mlx-community/SmolVLM2-500M-Video-Instruct-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mlx-community/SmolVLM2-500M-Video-Instruct-mlx with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("mlx-community/SmolVLM2-500M-Video-Instruct-mlx") model = AutoModelForMultimodalLM.from_pretrained("mlx-community/SmolVLM2-500M-Video-Instruct-mlx", device_map="auto") - MLX
How to use mlx-community/SmolVLM2-500M-Video-Instruct-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir SmolVLM2-500M-Video-Instruct-mlx mlx-community/SmolVLM2-500M-Video-Instruct-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Upload folder using huggingface_hub
Browse files- preprocessor_config.json +1 -1
preprocessor_config.json
CHANGED
|
@@ -29,7 +29,7 @@
|
|
| 29 |
"fps": 1,
|
| 30 |
"max_frames": 64,
|
| 31 |
"video_size": {
|
| 32 |
-
"longest_edge":
|
| 33 |
}
|
| 34 |
}
|
| 35 |
}
|
|
|
|
| 29 |
"fps": 1,
|
| 30 |
"max_frames": 64,
|
| 31 |
"video_size": {
|
| 32 |
+
"longest_edge": 512
|
| 33 |
}
|
| 34 |
}
|
| 35 |
}
|