Create README.md
#1
by
pcuenq
HF staff
- opened
README.md
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
datasets:
|
| 5 |
+
- HuggingFaceM4/the_cauldron
|
| 6 |
+
- HuggingFaceM4/Docmatix
|
| 7 |
+
pipeline_tag: video-text-to-text
|
| 8 |
+
language:
|
| 9 |
+
- en
|
| 10 |
+
base_model:
|
| 11 |
+
- HuggingFaceTB/SmolLM2-360M-Instruct
|
| 12 |
+
- google/siglip-base-patch16-512
|
| 13 |
+
- HuggingFaceTB/SmolVLM2-500M-Video-Instruct
|
| 14 |
+
tags:
|
| 15 |
+
- mlx
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
+
# HuggingFaceTB/SmolVLM2-500M-Video-Instruct-mlx
|
| 19 |
+
This model was converted to MLX format from [`HuggingFaceTB/SmolVLM2-500M-Video-Instruct`]() using mlx-vlm version **0.1.13**.
|
| 20 |
+
Refer to the [original model card](https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct) for more details on the model.
|
| 21 |
+
## Use with mlx
|
| 22 |
+
|
| 23 |
+
```bash
|
| 24 |
+
pip install -U mlx-vlm
|
| 25 |
+
```
|
| 26 |
+
|
| 27 |
+
```bash
|
| 28 |
+
python -m mlx_vlm.generate --model HuggingFaceTB/SmolVLM2-500M-Video-Instruct-mlx-8bit-skip-vision --image https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/bee.jpg --prompt "Can you describe this image?"
|
| 29 |
+
```
|