The model is quantized using https://github.com/WanBenLe/AutoAWQ-with-llava-v1.6.git

The source model is llava-hf/llava-v1.6-mistral-7b-hf

Downloads last month
21
Safetensors
Model size
1.52B params
Tensor type
I32
·
FP16
·
Inference Examples
Inference API (serverless) does not yet support transformers models for this pipeline type.