Qwen
/

Qwen2.5-VL-72B-Instruct

Image-Text-to-Text

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

vllm推理32k-128k输入

#17

by luckyZhangHu - opened 3 days ago

3 days ago

vllm推理，按默认的config.json中， max_position-embedding-128000, 是否能正常处理 32k-128k的长图文理解输入？

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

Tap or paste here to upload images

· Sign up or log in to comment