transformers
Add Siglip2Tokenizer to enforce training-time text preprocessing defaults
#43101
Merged

Add Siglip2Tokenizer to enforce training-time text preprocessing defaults #43101

vaibhav-research
vaibhav-research
vaibhav-research
fancyerii
fancyerii approved these changes on 2026-01-05
zucchini-nlp
zucchini-nlp commented on 2026-01-05
vaibhav-research
ArthurZucker
vaibhav-research
vaibhav-research
vaibhav-research
vaibhav-research vaibhav-research changed the title 43054: siglip2 text embedding test and document update 43054: siglip2 text embedding updated to default to lowercase 213 days ago
zucchini-nlp
zucchini-nlp commented on 2026-01-08
vaibhav-research vaibhav-research changed the title 43054: siglip2 text embedding updated to default to lowercase 43054: siglip2 text embedding default to lowercase 212 days ago
vaibhav-research vaibhav-research changed the title 43054: siglip2 text embedding default to lowercase 43054: Add Siglip2Tokenizer to enforce training-time text preprocessing defaults 212 days ago
ArthurZucker
ArthurZucker commented on 2026-01-09
zucchini-nlp
zucchini-nlp commented on 2026-01-09
vaibhav-research
vaibhav-research vaibhav-research force pushed from 368b6a4b to e25cc6c4 205 days ago
vaibhav-research vaibhav-research force pushed from e25cc6c4 to e1aafd13 205 days ago
vaibhav-research
zucchini-nlp
zucchini-nlp commented on 2026-01-16
zucchini-nlp
vaibhav-research vaibhav-research force pushed from 9993a749 to b1674823 202 days ago
vaibhav-research
vaibhav-research
vaibhav-research
vaibhav-research vaibhav-research force pushed from 0c8f75d7 to 64e9c82b 199 days ago
zucchini-nlp
zucchini-nlp commented on 2026-01-22
vaibhav-research vaibhav-research force pushed from 0379e11c to d1500569 198 days ago
github-actions
zucchini-nlp
zucchini-nlp approved these changes on 2026-01-23
zucchini-nlp
github-actions
HuggingFaceDocBuilderDev
github-actions
vaibhav-research
zucchini-nlp
ArthurZucker
ArthurZucker commented on 2026-01-23
vaibhav-research
vaibhav-research Add Siglip2Tokenizer with lowercase normalizer and tests
29f1c43d
vaibhav-research updated correct gemmatokenizer reference
f4419725
vaibhav-research Updated lowercase logic to keep it simple
4ff5b4bc
vaibhav-research added inegration test and removed _unk_id from tokenization
a5b330d5
vaibhav-research ruff fixes
e648a65e
vaibhav-research vaibhav-research force pushed from 4131a538 to e648a65e 196 days ago
vaibhav-research updated the doc
4ed6d375
zucchini-nlp
zucchini-nlp approved these changes on 2026-01-26
vaibhav-research Updated doc and conversion script
c913782e
vaibhav-research
vaibhav-research Merge branch 'main' into siglip2_text_embedding
251c6a8d
vaibhav-research Merge branch 'main' into siglip2_text_embedding
6c1e1ddc
vaibhav-research Merge branch 'main' into siglip2_text_embedding
bc6cca6a
vaibhav-research Merge branch 'main' into siglip2_text_embedding
0e9f60ce
vaibhav-research Merge branch 'main' into siglip2_text_embedding
9beaf584
zucchini-nlp
vaibhav-research Merge branch 'main' into siglip2_text_embedding
9de0edfa
vaibhav-research Merge branch 'main' into siglip2_text_embedding
c3608a2f
vaibhav-research
vaibhav-research Merge branch 'main' into siglip2_text_embedding
3c1683b0
vaibhav-research Merge branch 'main' into siglip2_text_embedding
15a11138
vaibhav-research Merge branch 'main' into siglip2_text_embedding
050c4201
vaibhav-research Merge branch 'main' into siglip2_text_embedding
ee811ee5
vaibhav-research Merge branch 'main' into siglip2_text_embedding
2d9876ea
ArthurZucker
ArthurZucker commented on 2026-01-28
ArthurZucker fix modular to skip type hinting when inheriting
34730e1f
ArthurZucker style
a9493205
github-actions
ArthurZucker ArthurZucker merged 1be63d94 into main 192 days ago
vaibhav-research
ArthurZucker
ArthurZucker
ArthurZucker commented on 2026-02-03
vaibhav-research vaibhav-research changed the title 43054: Add Siglip2Tokenizer to enforce training-time text preprocessing defaults Add Siglip2Tokenizer to enforce training-time text preprocessing defaults 124 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone