Yue Zhao
> I temporarily fixed the NetEase Music lyrics provider, while the QQ Music lyrics provider is still broken. > > Now iLyrics should be able to fetch the lyrics of...
ntapi v0.4.1 code may help :) https://github.com/MSxDOS/ntapi/blob/master/src/ntexapi.rs
@jomayeri Can you show all files in thudm/chatglm-6b folder? Are there tokenizer related files in it?
@jomayeri The folder should contain these files below. You can download the missing file from https://huggingface.co/THUDM/chatglm3-6b/tree/main 
> **Describe the bug** The behavior is same to what is reported in #4565 . When model.step() with zero3, Tensors are on different devices. I modified [stage3.py#L2117](https://github.com/microsoft/DeepSpeed/blob/master/deepspeed/runtime/zero/stage3.py#L2117) to self.fp32_partitioned_groups_flat[sub_group_id].grad.mul_(1. /...
Also interested.
@boluoweifenda Hi, I am interested in the implementation details of agents too. Can your clarify how the "181", "1019", "523" are caculated in F.2 part of your paper? I tried...
@boluoweifenda Thanks for your reply. I will learn to implement it like in gym.
i met the same problem when using cli script. Solved by adding --model-base