neuralmagic
/

Qwen2.5-VL-7B-Instruct-quantized.w8a8

Image-Text-to-Text

text-generation-inference

Inference Endpoints

8-bit precision

compressed-tensors

Model card Files Files and versions Community

Qwen2.5-VL-7B-Instruct-quantized.w8a8

4 contributors

History: 9 commits

mgoin's picture

pooya-davoodi-parasail's picture

pooya-davoodi-parasail

Remove image_processor_type (#1)

00529d9 verified 19 days ago