yuhai-china

Hi there, I encounter the same problem with GTX 970M 6G GPU for all ms coco 2014 train dataset ( about 400K images), but I train successfully for ms coco...

today I reinstall cutorch, and the issue is fixed.

> your model is too complicated, there are gradient issues if the equation is too large. Try smaller, fewer input variables, smaller function, look at the result and get an...

> Although I'm happy with the link you gave, I'm sure pykan is not just a toy. I'm not the author, but you'r conclusion was based on my personal understanding....

> You can download it here: https://fasttext.cc/docs/en/language-identification.html thanks, I want to find the mode to classify the web page whether it is low quality instead of language identification

> Hi, @yuhai-china Here's the model file that we trained ([link](https://drive.google.com/file/d/1DnsfpWWE0jFPCoYe6clwqb3Ub5Ac92s1/view?usp=share_link)). You can use the script [here](https://github.com/togethercomputer/RedPajama-Data/blob/main/data_prep/cc/classifier/classify.py) to load the model and run inference. > > I will also add...

I belive that you test is not corret, for llama-7B model ,2.20 requests/s or 1.03 requests/s are both too low .