Skip to content

Instantly share code, notes, and snippets.

View soran-ghaderi's full-sized avatar

Soran Ghaderi soran-ghaderi

View GitHub Profile

References

This GitHub Gist contains the references used in the Medium article titled "The Map Of Transformers. Broad overview of Transformers research" In the article, I provide an in-depth overview of various transformer variants proposed in recent years, highlighting their unique features and improvements.

The references included in this gist serve as the sources and inspirations for the information and insights presented in the article. They encompass a wide range of papers and research works that have contributed to the advancements in transformer models, including:

[1] Lin, T., Wang, Y., Liu, X. and Qiu, X., 2022. A survey of transformers. arXiv:2106.04554v2 [cs.LG]

@soran-ghaderi
soran-ghaderi / gist:edaff73aedbb6aee91c78bb887dd19bc
Created December 25, 2020 02:44
Solved: docs: Could not load dynamic library 'libcublas.so.10'
In case you ran into this error after installing cuda-10.1, here is what you can do:
Since cuda-10.1 installs the libraries in both /usr/local/cuda-10.1 and /usr/local/cuda-10.2 and tensorflow can't find them, you should add both of this paths to the ".bashrc" file as LD_LIBRARY_PATH.
Now:
1. open terminal:
sudo gedit ~/.bashrc or sudo vim ~/.bashrc
2. Add this line to the end of file:
export LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/cuda-10.1/lib64:/usr/local/cuda-10.2/lib64:/usr/local/cuda/extras/CUPTI/lib64:$LD_LIBRARY_PATH