HongCheng
HongCheng
https://github.com/XiaoyangBi/llm-universe/pull/1 楼主两天没回了， 可以先合并吧， 我可以后面帮着再提一个来修改notebook @0-yy-0
Maybe it is an alternative without specifying the version of tokenizer
@LinB203 what's the meaning of 'not enough', this project have shown several inference samples, may I ask you how much computing resource used to generate them for training a model?...
thanks for your reply
> > > I can support the work of fine-tuning Video-VQVAE on higher resolution. **So can you give me the training settings?** I can train multiple versions of the model...
Here is the direct link (https://github.com/mini-sora/minisora/tree/main#dataset) to the Minisora Dataset. Our team is updating this section with more datasets (available in one or two hours), so please stay tuned and...
Is there any public open-source “Synthetic video created by game engines or 3D representations” data or related research works?
Here I want to share what I have done with nuscene mini dataset and this code (even it is with some Chinese, I help this could help people want to...
@songhan @zhijian-liu @hopef @K-Shao I am sorry for this @ to you, could you please look at this issue and give me some hints? Thank you very much~~
I find the solution in here. [link](https://github.com/mit-han-lab/bevfusion/issues/480#issuecomment-1667112241)