vimarsh/repro-a-capacity-based-rationale-for-multi-head-attention
0
Update logbook: Reproduction: A Capacity-Based Rationale for Multi-Head Attention
Update logbook: Reproduction: A Capacity-Based Rationale for Multi-Head Attention
initial commit
Update logbook: Reproduction: A Capacity-Based Rationale for Multi-Head Attention
Update logbook: Reproduction: A Capacity-Based Rationale for Multi-Head Attention
initial commit