JettHu
JettHu
Not support yet. As an NLP model(LLM), t5 uses the entire sentence to encode, so t5 can actually fully understand your semantics. I think the weight of a certain word...
t5 模型是哪个链接下载的，以及 transfomers 版本号是多少
@FadySaeed what is your `transfomers` version?
@FadySaeed Run in the terminal and in your comfyui python environment: `pip list | grep transfomers`
@FadySaeed @ranfengqaq Sorry, the reply is a bit slow during the holidays. Can you check the contents of your `tokenizer.json`? The location is `models/ella_encoder/models--google--flan-t5-xl--text_encoder/tokenizer.json` If correct, it should be a...
Both 4.38.2 and 4.40.2 can run on my device. Check whether some model files are missing.
> > @JettHu great, works now. thanks. > > can you pleas explain what you did? facing same issue Check if your t5 encode is downloaded correctly.
Don’t know if there is a gap between the implementation and the paper. Needs to be jointly debugged with algorithm engineers. We'll look at this next week.
@budui Take a look at this
The f8 mode is not supported yet. I will take a look at this issue this week.