Hugging Face's logo

vanch007
/
Huihui-MiniCPM-V-4.6-abliterated-mlx-nvfp4

Image-Text-to-Text
MLX
Safetensors
minicpmv4_6
minicpm-v
multimodal
conversational
4-bit precision
Model card Files
xet
 Community

Huihui-MiniCPM-V-4.6-abliterated-mlx-nvfp4

Converted from huihui-ai/Huihui-MiniCPM-V-4.6-abliterated with mlx-vlm from the current main branch.

Conversion

  • Source: huihui-ai/Huihui-MiniCPM-V-4.6-abliterated
  • Format: MLX
  • Quantization: bfloat16 + nvfp4
  • Processor files: processor_config.json + preprocessor_config.json

Smoke test

  • Prompt: Describe this image in one sentence.
  • Image: 64x64 solid red PNG
  • Result: The image is entirely filled with a solid red color.

Usage 

python -m mlx_vlm.generate --model vanch007/Huihui-MiniCPM-V-4.6-abliterated-mlx-nvfp4 --max-tokens 32 --temperature 0.0 --trust-remote-code --prompt "Describe this image in one sentence." --image <path_to_image>
Downloads last month
207
Safetensors
Model size
1B params
Tensor type
BF16
路
U8
路
U32
路
MLX
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
Image-Text-to-Text
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for vanch007/Huihui-MiniCPM-V-4.6-abliterated-mlx-nvfp4

Base model

openbmb/MiniCPM-V-4.6
Finetuned
huihui-ai/Huihui-MiniCPM-V-4.6-abliterated
Quantized
(5)
this model