Instructions to use mlx-community/idefics2-8b-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/idefics2-8b-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/idefics2-8b-4bit") config = load_config("mlx-community/idefics2-8b-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
- Atomic Chat
Download config.json from mlx-community/idefics2-8b-4bit: direct link, hf CLI and curl.
- Browser
- Download file 840 Bytes
-
https://huggingface.co/mlx-community/idefics2-8b-4bit/resolve/main/config.json
- Command line
-
hf download hf://mlx-community/idefics2-8b-4bit/config.json
-
curl -L -o config.json https://huggingface.co/mlx-community/idefics2-8b-4bit/resolve/main/config.json
840 Bytes
| { | |
| "architectures": [ | |
| "Idefics2ForConditionalGeneration" | |
| ], | |
| "image_token_id": 32001, | |
| "model_type": "idefics2", | |
| "perceiver_config": { | |
| "model_type": "idefics2" | |
| }, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 4 | |
| }, | |
| "text_config": { | |
| "max_position_embeddings": 32768, | |
| "model_type": "mistral", | |
| "pad_token_id": 0, | |
| "rms_norm_eps": 1e-05, | |
| "vocab_size": 32003 | |
| }, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.39.0.dev0", | |
| "use_cache": true, | |
| "vision_config": { | |
| "hidden_size": 1152, | |
| "image_size": 980, | |
| "intermediate_size": 4352, | |
| "model_type": "idefics2", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 27, | |
| "patch_size": 14 | |
| } | |
| } |