hayleeXinyi

For densenet161, Top 1 err: tensor(0.2350) Top 5 err: tensor(0.0520)

+1

我的也是。

Thanks for answering! I then downloaded the file with the following command and it no longer shows an error. `git-lfs clone https://huggingface.co/decapoda-research/llama-13b-hf` But it still does not merge the weights....

> 很可能您没有足够的 RAM（128Gb 转换成功） I only have around 64G of RAM, which means this won't run up on my GPU? Is there any possible solution?

> Thank you so much!!!!! I solved this problem by expanding the virtual memory.

我试过了transformers的三个安装形式https://huggingface.co/docs/transformers/installation#installing-from-source还有作者原来带有哈希的方式，全部都不可以。解决了一个又一个问题，跑了一下午还没跑起来。建议作者还是把环境搞好再上传吧。不要浪费大家的时间

change to this `count = 0 for channel, mean, std in zip(denormalized[0], means, stds): denormalized[0][count] = denormalized[0][count].mul(std) denormalized[0][count] = denormalized[0][count].add(mean) count+=1` the key is change `channel.mul_(std).add_(mean)` to `denormalized[0][count] = denormalized[0][count].mul(std)`...