chaoyinshe

/

EchoVLM

like 2

This error occurs because Qwen2VLMOEForConditionalGeneration is not available in the official transformers library. If you haven't integrated this custom model into the transformers library source code, you should import it directly from your local module instead.
from EchoVLM import Qwen2VLMOEForConditionalGeneration

ImportError: cannot import name 'Qwen2VLMOEForConditionalGeneration' from 'transformers'
Please see the latest pre-release of Echovlm V2 based on Lingshu. This version is based on qwen2.5vl, requires no code modifications, and is used exactly the same as qwen2.5vl. It also supports vLLM acceleration and performs better in clinical trials because this version uses a more rigorous data cleaning pipeline.