Guolin Ke

Thank you @shiyu1994 , finally, we can merge this PR. The next step is to remove the old categorical features supports and update the documentations accordingly.

@jameslamb can you check the R's part?

Hi @StrikerRUS , yeah, we may have 4.0.0 release, there are sereval on-going works need to in 4.0.0 as well. I think we can release a 3.2.0 stable release recently,...

The calculation of them in merged in the above bmm. And 0,0 is p0 \dot p0, 1,1 is p1 \dot p1.

oh, in paper, the \theta_1 and \theta_2 are for better demonstration, they are actually calculated by the p0 and p1. I think you understand p0 \dot p0. p1 \dot p1...

refer to this script: https://github.com/guolinke/TUPE/blob/master/preprocess/glue/process.sh

This line https://github.com/guolinke/TUPE/blob/master/preprocess/glue/process.sh#L27 ？ I used the default g++ in the ubuntu 20.04

`model_2_ft`. The CUDA kernels are installed in the docker, you can also install the uni-core by yourself.

maybe you can try our pre-compiled wheel (https://github.com/dptech-corp/Uni-Core/releases/tag/0.0.1), we also use the wheel in the colab server. For the docker version, you can try: ```shell docker pull dptechnology/unifold:latest-pytorch1.11.0-cuda11.3 docker run...

it is quite simple, first download the wheel according to your python, pytorch, cuda version, and then run ``` pip3 -q install "unicore-0.0.1+cu113torch1.12.1-cp37-cp37m-linux_x86_64.whl" ``` the "unicore-0.0.1+cu113torch1.12.1-cp37-cp37m-linux_x86_64.whl" could be replaced to...