skqszy123
skqszy123
> 解决了么@skqszy123 没有啊
> 在文件Unzip.java,函数extractAll 63L下增加 > progressMonitor.setResult(ProgressMonitor.RESULT_WORKING); > 不然直接就走到成功回调了 确实
> set `attn_implementation="eager"` in configuration make the changes here > > ``` > import torch > from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor > model_path = "Qwen/Qwen2.5-VL-3B-Instruct" > model = Qwen2_5_VLForConditionalGeneration.from_pretrained(model_path, torch_dtype=torch.bfloat16,attn_implementation="eager",device_map="mps",low_cpu_mem_usage=True)...