vikarti.anatra/blt
1
0
Fork 0
mirror of https://github.com/facebookresearch/blt.git synced 2025-09-02 10:39:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Cast int sample id to str

Browse source
This commit is contained in:
Srini Iyer 2025-04-09 00:21:48 +00:00
parent 138c2f3494
commit 6a6a871c68
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
bytelatent/data/iterators/arrow_iterator.py
View file

@ -215,7 +215,7 @@ class ArrowFileIterator(StatefulIterator):
raise ValueError(f"Unknown file format: {self.file_format}") raise ValueError(f"Unknown file format: {self.file_format}")
for i in range(len(sample_ids)): for i in range(len(sample_ids)):
out = BltExample( out = BltExample(
sample_id=sample_ids[i], sample_id=str(sample_ids[i]),
entropies=entropies[i] if entropies is not None else None, entropies=entropies[i] if entropies is not None else None,
text=texts[i], text=texts[i],
tokens=None, tokens=None,
@ -249,7 +249,7 @@ class ArrowFileIterator(StatefulIterator):
raise ValueError(f"Unknown file format: {self.file_format}") raise ValueError(f"Unknown file format: {self.file_format}")
for i in range(len(sample_ids)): for i in range(len(sample_ids)):
out = BltExample( out = BltExample(
sample_id=sample_ids[i], sample_id=str(sample_ids[i]),
entropies=entropies[i] if entropies is not None else None, entropies=entropies[i] if entropies is not None else None,
text=texts[i], text=texts[i],
tokens=None, tokens=None,