mesolitica
/

llava-v1.6-vicuna-13b-hf-awq

Image-Text-to-Text

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

Llava-1.6 13B AWQ

You need to use this forked, https://github.com/WanBenLe/AutoAWQ-with-llava-v1.6

Downloads last month: 23

Safetensors

Model size

2.36B params

Tensor type

I32

·

BF16

·

FP16

·

Inference API

Image-Text-to-Text

Inference API (serverless) does not yet support transformers models for this pipeline type.