How to use GreenBitAI/DeepSeek-V4.1-Flash-4bit-paged 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("GreenBitAI/DeepSeek-V4.1-Flash-4bit-paged") config = load_config("GreenBitAI/DeepSeek-V4.1-Flash-4bit-paged") # 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)
https://huggingface.co/GreenBitAI/DeepSeek-V4.1-Flash-4bit-paged/resolve/main/engram_token_map.json
hf download hf://GreenBitAI/DeepSeek-V4.1-Flash-4bit-paged/engram_token_map.json
curl -L -o engram_token_map.json https://huggingface.co/GreenBitAI/DeepSeek-V4.1-Flash-4bit-paged/resolve/main/engram_token_map.json
