Image-Text-to-Text
MLX
Safetensors
English
qwen2_5_vl
multimodal
computer-use
cua
web-agent
agent
vision-language
conversational
4-bit precision
Instructions to use mlx-community/Fara-7B-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Fara-7B-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/Fara-7B-4bit") config = load_config("mlx-community/Fara-7B-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
Add MLX 4-bit conversion of microsoft/Fara-7B with vision preserved and weight-level fidelity vs bf16
cf74b8e verified Download tokenizer_config.json from mlx-community/Fara-7B-4bit: direct link, hf CLI and curl.
- Browser
- Download file 421 Bytes
-
https://huggingface.co/mlx-community/Fara-7B-4bit/resolve/main/tokenizer_config.json
- Command line
-
hf download hf://mlx-community/Fara-7B-4bit/tokenizer_config.json
-
curl -L -o tokenizer_config.json https://huggingface.co/mlx-community/Fara-7B-4bit/resolve/main/tokenizer_config.json
421 Bytes
| { | |
| "add_prefix_space": false, | |
| "backend": "tokenizers", | |
| "bos_token": null, | |
| "clean_up_tokenization_spaces": false, | |
| "eos_token": "<|im_end|>", | |
| "errors": "replace", | |
| "is_local": true, | |
| "local_files_only": false, | |
| "model_max_length": 131072, | |
| "pad_token": "<|endoftext|>", | |
| "processor_class": "Qwen2_5_VLProcessor", | |
| "split_special_tokens": false, | |
| "tokenizer_class": "Qwen2Tokenizer", | |
| "unk_token": null | |
| } | |