zhangyiss/mlx
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx.git synced 2025-09-03 06:14:43 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Spelling fixes in transformer.py (#59)

Browse Source
This commit is contained in:
Zach Schillaci
2023-12-07 22:32:09 +01:00
committed by GitHub
parent bf410cb85e
commit d11d77e581
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
python/mlx/nn/layers/transformer.py
View File

@@ -16,7 +16,7 @@ class MultiHeadAttention(Module):
new values by aggregating information from the input values according to
the similarities of the input queries and keys.
All inputs as well as the output are lineary projected without biases.
All inputs as well as the output are linearly projected without biases.
MultiHeadAttention also expects an additive attention mask that should be
broadcastable with (batch, num_heads, # queries, # keys). The mask should
@@ -48,7 +48,7 @@ class MultiHeadAttention(Module):
if (dims % num_heads) != 0:
raise ValueError(
f"The input feature dimensions should be divisble by the number of heads ({dims} % {num_heads}) != 0"
f"The input feature dimensions should be divisible by the number of heads ({dims} % {num_heads}) != 0"
)
query_input_dims = query_input_dims or dims