Image-Text-to-Text
MLX
Safetensors
kimi_vl
agent
video
screenspot
long-context
conversational
custom_code
4-bit precision
Instructions to use internetoftim/Kimi-VL-A3B-Instruct-mlx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use internetoftim/Kimi-VL-A3B-Instruct-mlx-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("internetoftim/Kimi-VL-A3B-Instruct-mlx-4bit") config = load_config("internetoftim/Kimi-VL-A3B-Instruct-mlx-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
| { | |
| "added_tokens_decoder": { | |
| "163584": { | |
| "content": "[BOS]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "163585": { | |
| "content": "[EOS]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "163586": { | |
| "content": "<|im_end|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "163587": { | |
| "content": "<|im_user|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "163588": { | |
| "content": "<|im_assistant|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "163594": { | |
| "content": "<|im_system|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "163601": { | |
| "content": "<|im_middle|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "163838": { | |
| "content": "[PAD]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| }, | |
| "163839": { | |
| "content": "[UNK]", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false, | |
| "special": true | |
| } | |
| }, | |
| "auto_map": { | |
| "AutoTokenizer": [ | |
| "tokenization_moonshot.TikTokenTokenizer", | |
| null | |
| ] | |
| }, | |
| "backend": "custom", | |
| "bos_token": "[BOS]", | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "[EOS]", | |
| "extra_special_tokens": [ | |
| "<|im_end|>", | |
| "<|im_middle|>", | |
| "<|im_user|>", | |
| "<|im_assistant|>", | |
| "<|im_system|>" | |
| ], | |
| "is_local": true, | |
| "local_files_only": true, | |
| "model_max_length": 1048576, | |
| "pad_token": "[PAD]", | |
| "processor_class": "KimiVLProcessor", | |
| "tokenizer_class": "TikTokenTokenizer", | |
| "unk_token": "[UNK]" | |
| } | |