Add Siglip2Tokenizer to enforce training-time text preprocessing defaults #43101
fancyerii
approved these changes
on 2026-01-05
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
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
changed the title 43054: siglip2 text embedding default to lowercase 43054: Add Siglip2Tokenizer to enforce training-time text preprocessing defaults 212 days ago
Add Siglip2Tokenizer with lowercase normalizer and tests
29f1c43d
updated correct gemmatokenizer reference
f4419725
Updated lowercase logic to keep it simple
4ff5b4bc
added inegration test and removed _unk_id from tokenization
a5b330d5
ruff fixes
e648a65e
updated the doc
4ed6d375
Updated doc and conversion script
c913782e
Merge branch 'main' into siglip2_text_embedding
251c6a8d
Merge branch 'main' into siglip2_text_embedding
6c1e1ddc
Merge branch 'main' into siglip2_text_embedding
bc6cca6a
Merge branch 'main' into siglip2_text_embedding
0e9f60ce
Merge branch 'main' into siglip2_text_embedding
9beaf584
Merge branch 'main' into siglip2_text_embedding
9de0edfa
Merge branch 'main' into siglip2_text_embedding
c3608a2f
Merge branch 'main' into siglip2_text_embedding
3c1683b0
Merge branch 'main' into siglip2_text_embedding
15a11138
Merge branch 'main' into siglip2_text_embedding
050c4201
Merge branch 'main' into siglip2_text_embedding
ee811ee5
Merge branch 'main' into siglip2_text_embedding
2d9876ea
fix modular to skip type hinting when inheriting
34730e1f
style
a9493205
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
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub