graldij/transformer-fusion
Official repository of the "Transformer Fusion with Optimal Transport" paper, published as a conference paper at ICLR 2024.
Python
Issues
- 0
- 1
How you ensure T_qk@T_qk^T=I?
#4 opened by daidaiershidi - 0
Configurations for experiments in paper.
#3 opened by davidleejy - 1