Zhuoshi Pan

@Nonbiuld 老哥，我也注意到这个问题了，请问更改之后效果如何？

thanks for your code in karras_diffusion.py. But I've noticed that the effect of the superres heavily rely on some hyperparameters when using cd_bedroom256_l2.pt, say **ts** in https://github.com/openai/consistency_models/blob/6d26080c58244555c031dbc63080c0961af74200/cm/karras_diffusion.py#LL838C8-L838C8 So are there...

Best wishes.

Hi @56wangyun, thanks for providing the detailed information. I believe the difference in results may indeed be attributed to the use of different Mistral models. As mentioned in the "Mistral-7B...

Hi @xvyaward, thanks for your interest and the very detailed description. 1. The **multifieldqa_zh** should be excluded here. As for Chinese, we have evaluated the performance of LLMLingua-2 on Chinese...

Hi, @jzhang538, thank you for raising the question! I think there are two reasons that may lead to this issue. The first is the parameters of LLMLingua, such as iterative_size...

Hi @xvyaward, thanks for your interest and the very detailed description. 1. Could you please share more information on how you use the mistral model for inference? As the sampling...

> > Hi @xvyaward, thanks for your interest and the very detailed description. > > > > 1. Could you please share more information on how you use the mistral...

Hi @pzs19, sorry for the misunderstanding. In the last response, I mean if you want to add special tokens during training, you need to modify our training code. In our...

Thank you for raising the questions. There is point to point response: - The target LLM is GPT-3.5-Turbo-0613, so vllm is not used. - The latency experiment is conducted on...