transformers
[vllm + v5 fix] handle TokenizersBackend fallback properly for v5
#44255
Merged

[vllm + v5 fix] handle TokenizersBackend fallback properly for v5 #44255

ArthurZucker merged 48 commits into main from bad_models_update
itazap
itazap itazap requested a review from hmellor hmellor 122 days ago
HuggingFaceDocBuilderDev
itazap itazap requested a review from ArthurZucker ArthurZucker 122 days ago
ArthurZucker
ArthurZucker commented on 2026-02-24
ArthurZucker
itazap itazap requested a review from ArthurZucker ArthurZucker 122 days ago
itazap itazap changed the title [vllm + v5 fix] update deepseek v2 tokenizer class for v5 [vllm + v5 fix] handle TokenizersBackend fallback properly for v5 120 days ago
ArthurZucker
ArthurZucker commented on 2026-02-27
ArthurZucker
ArthurZucker approved these changes on 2026-03-02
itazap itazap force pushed from 575d5664 to 2e03e15b 116 days ago
ArthurZucker
ArthurZucker commented on 2026-03-02
ArthurZucker
github-actions
itazap itazap requested a review from ArthurZucker ArthurZucker 115 days ago
github-actions
ArthurZucker
ArthurZucker commented on 2026-03-03
ArthurZucker
ArthurZucker commented on 2026-03-03
update deepseek v2 for tokenizers v5
7db52901
adding remote code fix
5ef00618
fix deepseek name
7be0c578
itazap handle spm conversion from proto only when overriding bad_models
1d227013
itazap add script to compare xlni and code_search_net output of 2 tokenizers
43a07e1d
itazap tiktoken models support
ffb5f095
itazap fix tests
c1a3a0dd
itazap testssss
43078316
itazap fix gemma
1bbe2578
itazap apply some feedback
b5d0badc
itazap paligemma processor tests fix
b7547e42
itazap add relevant changes from #44298
f5fd8400
itazap json serializable fix
2b9efdf0
itazap add more xlni cases
e1411666
itazap t5 fix
ae253810
itazap ruff check code quality
77120a21
itazap missed file for t5 test fix
3b053b05
itazap modular failures
a5542cca
itazap other modular fixes
95bba6ca
itazap tiktoken.model test
7d46f77f
itazap more feedback updates!
be29c606
itazap fixing models so AutoTokenizer == TokenizersBackend - aligning with c…
53753c31
itazap seamless m4t
47457459
itazap missed the most important files
cbda0cac
itazap Revert "missed the most important files"
e5c8a2f7
itazap undo changes to big bird , bert, seamless
8bf6df09
itazap setup and qual
df12cc4e
itazap itazap force pushed from 02766a30 to df12cc4e 114 days ago
itazap lasr
08b91c68
itazap t5
a7c2435b
ArthurZucker
ArthurZucker approved these changes on 2026-03-04
itazap dpr bert
d5e9aba1
itazap xlmroberta
ceeb3197
itazap reformer
b512fc70
itazap nllb
0c958427
ArthurZucker style and shit
34d83ed7
ArthurZucker update
5c8af86f
ArthurZucker fix
4d068711
ArthurZucker extract the charsmap
2159e92f
ArthurZucker fix mbart?
db0c5b58
ArthurZucker style
31ff32d2
itazap nllb and test tok common read spm precompiled charsmap
083ec509
ArthurZucker fix whisper?
a4fc098f
ArthurZucker Merge branch 'bad_models_update' of github.com:huggingface/transforme…
2710fadf
itazap nllb
969c0fc6
ArthurZucker checked on v4!
47a772ae
ArthurZucker Merge branch 'bad_models_update' of github.com:huggingface/transforme…
8039c2b6
ArthurZucker fix repo
e3d30250
github-actions
ArthurZucker fix lasr
6edc1d37
ArthurZucker style
dade5e63
ArthurZucker ArthurZucker merged fd6bc380 into main 114 days ago
ArthurZucker ArthurZucker deleted the bad_models_update branch 114 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone