Hugging Face's logo

mlx-community
/
Qwen2-VL-7B-Instruct-abliterated-6bit

Image-Text-to-Text
Transformers
Safetensors
MLX
English
qwen2_vl
chat
abliterated
uncensored
conversational
text-generation-inference
Inference Endpoints
Model card Files Community

mlx-community/Qwen2-VL-7B-Instruct-abliterated-6bit

This model was converted to MLX format from huihui-ai/Qwen2-VL-7B-Instruct-abliterated using mlx-vlm version 0.1.13. Refer to the original model card for more details on the model.

Use with mlx 

pip install -U mlx-vlm

python -m mlx_vlm.generate --model mlx-community/Qwen2-VL-7B-Instruct-abliterated-6bit --max-tokens 100 --temp 0.0 --prompt "Describe this image." --image <path_to_image>
Downloads last month
11
Safetensors
Model size
1.82B params
Tensor type
FP16
·
U32
·
Inference Providers NEW
Image-Text-to-Text
This model is not currently available via any of the supported Inference Providers.

Model tree for mlx-community/Qwen2-VL-7B-Instruct-abliterated-6bit

Base model

Qwen/Qwen2-VL-7B
Finetuned
Qwen/Qwen2-VL-7B-Instruct
Finetuned
(185)
this model

Collection including mlx-community/Qwen2-VL-7B-Instruct-abliterated-6bit