Image-Text-to-Text
MLX
Safetensors
cohere_compass
mlx-vlm
openmed
openmedkit
apple-silicon
on-device
vision
multimodal
clinical
medical
privacy
native-resolution
conversational
Instructions to use OpenMed/North-Micro-Vision-Instruct-bf16-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use OpenMed/North-Micro-Vision-Instruct-bf16-mlx 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("OpenMed/North-Micro-Vision-Instruct-bf16-mlx") config = load_config("OpenMed/North-Micro-Vision-Instruct-bf16-mlx") # 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
- Atomic Chat
| { | |
| "add_prefix_space": false, | |
| "backend": "tokenizers", | |
| "bos_token": "<BOS_TOKEN>", | |
| "clean_up_tokenization_spaces": false, | |
| "cls_token": "<CLS>", | |
| "eos_token": "<|END_OF_TURN_TOKEN|>", | |
| "errors": "replace", | |
| "image_token": "<|IMAGE_PAD|>", | |
| "is_local": true, | |
| "legacy": true, | |
| "local_files_only": true, | |
| "mask_token": "<MASK_TOKEN>", | |
| "max_pixels": 3868706, | |
| "min_pixels": 16384, | |
| "model_max_length": 1000000000000000019884624838656, | |
| "model_specific_special_tokens": { | |
| "image_token": "<|IMAGE_PAD|>", | |
| "video_token": "<|VIDEO_PAD|>", | |
| "vision_end_token": "<|VISION_END|>", | |
| "vision_start_token": "<|VISION_START|>" | |
| }, | |
| "pad_token": "<PAD>", | |
| "padding_side": "right", | |
| "processor_class": "CohereCompassProcessor", | |
| "sep_token": "<SEP>", | |
| "sp_model_kwargs": {}, | |
| "spaces_between_special_tokens": false, | |
| "tokenizer_class": "CohereTokenizer", | |
| "unk_token": "<UNK>", | |
| "use_default_system_prompt": false, | |
| "video_token": "<|VIDEO_PAD|>", | |
| "vision_end_token": "<|VISION_END|>", | |
| "vision_start_token": "<|VISION_START|>" | |
| } | |