bug fixed in the forward method of LearnedAlibiPositionalBias class

lucidrains / x-transformers

A concise but complete full-attention transformer with a set of promising experimental features from various papers

MIT License

4.63k stars 395 forks source link

Closed taemincho closed 1 year ago

taemincho commented 1 year ago

Deleted variables that were not previously removed

lucidrains commented 1 year ago

@taemincho thanks!