PoliBa-DeepLearning/NanoSocrates
2
0
Fork 0
Code Issues 3 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Added small dataset

Browse Source
This commit is contained in:
Christian Risi
2025-10-07 20:44:40 +02:00
parent 3f465991f0
commit d1ff88da82
5 changed files with 14 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
Project_Model/Libs/Transformer/Utils/post_tokenization.py
View File

@@ -45,9 +45,8 @@ def normalize_sequence(
pad_token: int,
end_token: int,
) -> tuple[list[int], list[bool]]:
new_sequence = pad_sequence(sequence, max_length, pad_token)
new_sequence = truncate_sequence(new_sequence, max_length, end_token)
new_sequence = truncate_sequence(sequence, max_length, end_token)
new_sequence = pad_sequence(new_sequence, max_length, pad_token)
PADDING_MASK = create_padding_mask(new_sequence, pad_token)
return (new_sequence, PADDING_MASK)