Image-Text-to-Text
MLX
Safetensors
English
Chinese
visionpsy_nano
vlm
vision-language-model
apple-silicon
siglip2
smollm2
conversational
Instructions to use KaedeTai/VisionPsy-Nano-460M-Flash-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use KaedeTai/VisionPsy-Nano-460M-Flash-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("KaedeTai/VisionPsy-Nano-460M-Flash-MLX") config = load_config("KaedeTai/VisionPsy-Nano-460M-Flash-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
| { | |
| "processor_class": "VisionPsyNanoProcessor", | |
| "auto_map": { | |
| "AutoProcessor": "processing_visionpsynano.VisionPsyNanoProcessor" | |
| }, | |
| "is_flash": true, | |
| "vit_img_size": 512, | |
| "max_img_size": 2048, | |
| "inference_max_img_size": null, | |
| "resize_to_max_side_len": false, | |
| "resize_min_side_len": 512, | |
| "mp_image_token_length": 64, | |
| "lm_max_position_embeddings": 8192, | |
| "lm_tokenizer": "HuggingFaceTB/SmolLM2-360M-Instruct", | |
| "lm_chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}", | |
| "vlm_extra_tokens": { | |
| "image_token": "<|image|>", | |
| "global_image_token": "<|global_image|>", | |
| "r1c1": "<row_1_col_1>", | |
| "r1c2": "<row_1_col_2>", | |
| "r1c3": "<row_1_col_3>", | |
| "r1c4": "<row_1_col_4>", | |
| "r1c5": "<row_1_col_5>", | |
| "r1c6": "<row_1_col_6>", | |
| "r1c7": "<row_1_col_7>", | |
| "r1c8": "<row_1_col_8>", | |
| "r2c1": "<row_2_col_1>", | |
| "r2c2": "<row_2_col_2>", | |
| "r2c3": "<row_2_col_3>", | |
| "r2c4": "<row_2_col_4>", | |
| "r2c5": "<row_2_col_5>", | |
| "r2c6": "<row_2_col_6>", | |
| "r2c7": "<row_2_col_7>", | |
| "r2c8": "<row_2_col_8>", | |
| "r3c1": "<row_3_col_1>", | |
| "r3c2": "<row_3_col_2>", | |
| "r3c3": "<row_3_col_3>", | |
| "r3c4": "<row_3_col_4>", | |
| "r3c5": "<row_3_col_5>", | |
| "r3c6": "<row_3_col_6>", | |
| "r3c7": "<row_3_col_7>", | |
| "r3c8": "<row_3_col_8>", | |
| "r4c1": "<row_4_col_1>", | |
| "r4c2": "<row_4_col_2>", | |
| "r4c3": "<row_4_col_3>", | |
| "r4c4": "<row_4_col_4>", | |
| "r4c5": "<row_4_col_5>", | |
| "r4c6": "<row_4_col_6>", | |
| "r4c7": "<row_4_col_7>", | |
| "r4c8": "<row_4_col_8>", | |
| "r5c1": "<row_5_col_1>", | |
| "r5c2": "<row_5_col_2>", | |
| "r5c3": "<row_5_col_3>", | |
| "r5c4": "<row_5_col_4>", | |
| "r5c5": "<row_5_col_5>", | |
| "r5c6": "<row_5_col_6>", | |
| "r5c7": "<row_5_col_7>", | |
| "r5c8": "<row_5_col_8>", | |
| "r6c1": "<row_6_col_1>", | |
| "r6c2": "<row_6_col_2>", | |
| "r6c3": "<row_6_col_3>", | |
| "r6c4": "<row_6_col_4>", | |
| "r6c5": "<row_6_col_5>", | |
| "r6c6": "<row_6_col_6>", | |
| "r6c7": "<row_6_col_7>", | |
| "r6c8": "<row_6_col_8>", | |
| "r7c1": "<row_7_col_1>", | |
| "r7c2": "<row_7_col_2>", | |
| "r7c3": "<row_7_col_3>", | |
| "r7c4": "<row_7_col_4>", | |
| "r7c5": "<row_7_col_5>", | |
| "r7c6": "<row_7_col_6>", | |
| "r7c7": "<row_7_col_7>", | |
| "r7c8": "<row_7_col_8>", | |
| "r8c1": "<row_8_col_1>", | |
| "r8c2": "<row_8_col_2>", | |
| "r8c3": "<row_8_col_3>", | |
| "r8c4": "<row_8_col_4>", | |
| "r8c5": "<row_8_col_5>", | |
| "r8c6": "<row_8_col_6>", | |
| "r8c7": "<row_8_col_7>", | |
| "r8c8": "<row_8_col_8>" | |
| } | |
| } | |