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") - 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
Manually update processor, for now. Part of https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct/commit/d52b9cddd52922722e9e0780315d209dd8311f45. (#1)
Browse files- Manually update processor, for now. Part of https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct/commit/d52b9cddd52922722e9e0780315d209dd8311f45. (7f8745f5ca6a2e975c55b9f08441d6c977b183e9)
- processor_config.json +1 -1
processor_config.json
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
{
|
| 2 |
"image_seq_len": 64,
|
| 3 |
-
"processor_class": "
|
| 4 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"image_seq_len": 64,
|
| 3 |
+
"processor_class": "SmolVLMProcessor"
|
| 4 |
}
|