Traducción al español del notebook "The Annotated Transformer" de Harvard NLP donde se explica e implementa el paper "Attention Is All You Need".
5
stars
3
forks
source link
Implementar "Masked Multi-Head Attention" con PyTorch (.py) #18
Open
mariagrandury opened 3 years ago
masked_multi_head_attention.py
masked_multi_head_attention
usando PyTorchpositional_encoding
add_and_norm