Ziyu jin
Ziyu jin
> [@zhouyang2002](https://github.com/zhouyang2002) [@Ziyu-Jin](https://github.com/Ziyu-Jin) Were you able to resolve this? I think it might be a problem with the my conda env. After I reinstalled the environment, it doesn't seem to...
> > > 可以参考 https://github.com/hiyouga/LLaMA-Factory/blob/main/examples/train_lora/qwen2vl_lora_sft.yaml 其中 identity 数据集是纯文本 > > > > > > 我试了一下，会卡着，不能训。。。load完数据后就卡在那了 > > 有更新吗，我也有这个需求，混合数据中纯文本部分尝试将'images'键的值设为空，和直接去掉都不行。 我也是，请问解决了吗
same
Qwen2.5vl的textvqa eval代码在哪里能找到呢？