RedHatAI
/

Qwen2-VL-72B-Instruct-FP8-dynamic

text-generation-inference

compressed-tensors

Model card Files Files and versions

Change max/min_pixels to longest/shortest_edge

#1

by pooya-davoodi-parasail - opened 27 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

pooya-davoodi-parasail

27 days ago

This is similar to https://huggingface.co/RedHatAI/Qwen2.5-VL-72B-Instruct-FP8-Dynamic/blob/main/preprocessor_config.json

Otherwise vllm fails to load the model.

Change max/min_pixels to longest/shortest_edge11b0d55b

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment