lucidrains/x-transformers
A simple but complete full-attention transformer with a set of promising experimental features from various papers
PythonMIT
Issues
- 0
Problem with cache and memory
#255 opened - 1
- 2
How to use "src_key_padding_mask"
#253 opened - 1
- 0
RoPE inconsistency (2-dim subspaces choice)
#250 opened