Instructions to use digitranslab/Megamind-v2-VL-low-4bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use digitranslab/Megamind-v2-VL-low-4bit-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Megamind-v2-VL-low-4bit-mlx digitranslab/Megamind-v2-VL-low-4bit-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -48,7 +48,7 @@ from mlx_vlm.prompt_utils import apply_chat_template
|
|
| 48 |
from mlx_vlm.utils import load_config
|
| 49 |
|
| 50 |
# Load the model
|
| 51 |
-
model_path = "
|
| 52 |
model, processor = load(model_path)
|
| 53 |
config = load_config(model_path)
|
| 54 |
|
|
@@ -69,7 +69,7 @@ print(output)
|
|
| 69 |
### Command Line
|
| 70 |
|
| 71 |
```bash
|
| 72 |
-
mlx_vlm.generate --model
|
| 73 |
```
|
| 74 |
|
| 75 |
## Intended Use
|
|
@@ -90,7 +90,7 @@ For more information, please refer to the original model: [digitranslab/Megamind
|
|
| 90 |
|
| 91 |
## Acknowledgments
|
| 92 |
|
| 93 |
-
- Original model by [
|
| 94 |
- [MLX](https://github.com/ml-explore/mlx) framework by Apple
|
| 95 |
- MLX conversion framework by [Prince Canuma](https://github.com/Blaizzy/mlx-vlm)
|
| 96 |
- Model conversion by [Incept5](https://incept5.ai)
|
|
|
|
| 48 |
from mlx_vlm.utils import load_config
|
| 49 |
|
| 50 |
# Load the model
|
| 51 |
+
model_path = "digitranslab/Megamind-v2-VL-low-4bit-mlx"
|
| 52 |
model, processor = load(model_path)
|
| 53 |
config = load_config(model_path)
|
| 54 |
|
|
|
|
| 69 |
### Command Line
|
| 70 |
|
| 71 |
```bash
|
| 72 |
+
mlx_vlm.generate --model digitranslab/Megamind-v2-VL-low-4bit-mlx --max-tokens 100 --prompt "Describe this image" --image path/to/image.jpg
|
| 73 |
```
|
| 74 |
|
| 75 |
## Intended Use
|
|
|
|
| 90 |
|
| 91 |
## Acknowledgments
|
| 92 |
|
| 93 |
+
- Original model by [Megamind](https://huggingface.co/digitranslab)
|
| 94 |
- [MLX](https://github.com/ml-explore/mlx) framework by Apple
|
| 95 |
- MLX conversion framework by [Prince Canuma](https://github.com/Blaizzy/mlx-vlm)
|
| 96 |
- Model conversion by [Incept5](https://incept5.ai)
|