Instructions to use hehua2008/Mistral-Small-3.2-24B-Instruct-2506-abliterated-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use hehua2008/Mistral-Small-3.2-24B-Instruct-2506-abliterated-MLX-8bit 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("hehua2008/Mistral-Small-3.2-24B-Instruct-2506-abliterated-MLX-8bit") config = load_config("hehua2008/Mistral-Small-3.2-24B-Instruct-2506-abliterated-MLX-8bit") # 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 hehua2008/Mistral-Small-3.2-24B-Instruct-2506-abliterated-MLX-8bit: direct link, hf CLI and curl.
- Browser
- Download file 1.52 kB
-
https://huggingface.co/hehua2008/Mistral-Small-3.2-24B-Instruct-2506-abliterated-MLX-8bit/resolve/main/config.json
- Command line
-
hf download hf://hehua2008/Mistral-Small-3.2-24B-Instruct-2506-abliterated-MLX-8bit/config.json
-
curl -L -o config.json https://huggingface.co/hehua2008/Mistral-Small-3.2-24B-Instruct-2506-abliterated-MLX-8bit/resolve/main/config.json
1.52 kB
| { | |
| "architectures": [ | |
| "Mistral3ForConditionalGeneration" | |
| ], | |
| "eos_token_id": 2, | |
| "image_token_index": 10, | |
| "model_type": "mistral3", | |
| "multimodal_projector_bias": false, | |
| "projector_hidden_act": "gelu", | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 8, | |
| "mode": "affine" | |
| }, | |
| "spatial_merge_size": 2, | |
| "text_config": { | |
| "attention_dropout": 0.0, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 32768, | |
| "max_position_embeddings": 131072, | |
| "model_type": "mistral", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 1000000000.0, | |
| "sliding_window": null, | |
| "use_cache": true, | |
| "vocab_size": 131072 | |
| }, | |
| "transformers_version": "4.50.0.dev0", | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "image_size": 1540, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "model_type": "pixtral", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 24, | |
| "patch_size": 14, | |
| "rope_theta": 10000.0 | |
| }, | |
| "vision_feature_layer": -1 | |
| } |