Rishab Jain

Hello there! This research is fascinating. I was wondering what layers were used in the architecture of your model. I see that there are biLSTM layers and a dropout layer:...

Not Enable to Use Make on Windows

1

`C:\Users\Pictures\cd-hit-v4.8.1-2019-0228>make g++ -fopenmp -DWITH_ZLIB -O2 cdhit-common.c++ -c process_begin: CreateProcess(NULL, g++ -fopenmp -DWITH_ZLIB -O2 cdhit-common.c++ -c, ...) failed. make (e=2): The system cannot find the file specified. make: *** [cdhit-common.o] Error...

70B Model is Using 200gb of VRAM

3

I am having trouble running inference on the 70b model as it is using additional CPU memory, possibly creating a bottleneck in performance. It is unable to load all 70b...