Image-Text-to-Text
MLX
Safetensors
mistral3
mistral-common
ministral
ministral-3
vision-language
multimodal
quantized
edge
4-bit precision
base-model
Instructions to use mlx-community/Ministral-3-14B-Base-2512-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Ministral-3-14B-Base-2512-4bit with MLX:
# Make sure mlx-vlm is installed # pip install --upgrade mlx-vlm from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config # Load the model model, processor = load("mlx-community/Ministral-3-14B-Base-2512-4bit") config = load_config("mlx-community/Ministral-3-14B-Base-2512-4bit") # Prepare input image = ["http://images.cocodataset.org/val2017/000000039769.jpg"] prompt = "Describe this image." # Apply chat template formatted_prompt = apply_chat_template( processor, config, prompt, num_images=1 ) # Generate output output = generate(model, processor, formatted_prompt, image) print(output) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Upload processor_config.json with huggingface_hub
Browse files- processor_config.json +7 -2
processor_config.json
CHANGED
|
@@ -4,6 +4,8 @@
|
|
| 4 |
"image_processor": {
|
| 5 |
"crop_size": null,
|
| 6 |
"data_format": "channels_first",
|
|
|
|
|
|
|
| 7 |
"do_center_crop": null,
|
| 8 |
"do_convert_rgb": true,
|
| 9 |
"do_normalize": true,
|
|
@@ -15,23 +17,26 @@
|
|
| 15 |
0.4578275,
|
| 16 |
0.40821073
|
| 17 |
],
|
| 18 |
-
"image_processor_type": "
|
| 19 |
"image_seq_length": null,
|
| 20 |
"image_std": [
|
| 21 |
0.26862954,
|
| 22 |
0.26130258,
|
| 23 |
0.27577711
|
| 24 |
],
|
|
|
|
| 25 |
"pad_size": null,
|
| 26 |
"patch_size": 14,
|
|
|
|
| 27 |
"resample": 3,
|
| 28 |
"rescale_factor": 0.00392156862745098,
|
|
|
|
| 29 |
"size": {
|
| 30 |
"longest_edge": 1540
|
| 31 |
}
|
| 32 |
},
|
| 33 |
"image_token": "[IMG]",
|
| 34 |
"patch_size": 14,
|
| 35 |
-
"processor_class": "
|
| 36 |
"spatial_merge_size": 2
|
| 37 |
}
|
|
|
|
| 4 |
"image_processor": {
|
| 5 |
"crop_size": null,
|
| 6 |
"data_format": "channels_first",
|
| 7 |
+
"device": null,
|
| 8 |
+
"disable_grouping": null,
|
| 9 |
"do_center_crop": null,
|
| 10 |
"do_convert_rgb": true,
|
| 11 |
"do_normalize": true,
|
|
|
|
| 17 |
0.4578275,
|
| 18 |
0.40821073
|
| 19 |
],
|
| 20 |
+
"image_processor_type": "PixtralImageProcessorFast",
|
| 21 |
"image_seq_length": null,
|
| 22 |
"image_std": [
|
| 23 |
0.26862954,
|
| 24 |
0.26130258,
|
| 25 |
0.27577711
|
| 26 |
],
|
| 27 |
+
"input_data_format": null,
|
| 28 |
"pad_size": null,
|
| 29 |
"patch_size": 14,
|
| 30 |
+
"processor_class": "PixtralProcessor",
|
| 31 |
"resample": 3,
|
| 32 |
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_tensors": null,
|
| 34 |
"size": {
|
| 35 |
"longest_edge": 1540
|
| 36 |
}
|
| 37 |
},
|
| 38 |
"image_token": "[IMG]",
|
| 39 |
"patch_size": 14,
|
| 40 |
+
"processor_class": "PixtralProcessor",
|
| 41 |
"spatial_merge_size": 2
|
| 42 |
}
|