neuralmagic
/

Qwen2.5-VL-72B-Instruct-quantized.w8a8

Image-Text-to-Text

text-generation-inference

Inference Endpoints

8-bit precision

compressed-tensors

Model card Files Files and versions Community

pooya-davoodi-parasail commited on 15 days ago

Commit

de445b0

·

verified ·

1 Parent(s): f005e30

Remove image_processor_type

This is similar to the change in https://huggingface.co/neuralmagic/Qwen2.5-VL-72B-Instruct-FP8-Dynamic/discussions/2

Files changed (1) hide show

preprocessor_config.json +0 -1

preprocessor_config.json CHANGED Viewed

@@ -8,7 +8,6 @@
     0.4578275,
     0.40821073
   ],
-  "image_processor_type": "Qwen2_5_VLImageProcessor",
   "image_std": [
     0.26862954,
     0.26130258,

     0.4578275,
     0.40821073
   ],
   "image_std": [
     0.26862954,
     0.26130258,