Skip to content

Fix/transformers v5 gemma tokenizer #1030

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Tcc0403 merged 1 commit into from
Jan 20, 2026
+7 −7
Merged

Fix/transformers v5 gemma tokenizer #1030

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions test/convergence/bf16/test_mini_models_multimodal.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@
from datasets import load_dataset
from torch.utils.data import DataLoader
from transformers import PreTrainedTokenizerFast
from transformers.models.gemma.tokenization_gemma_fast import GemmaTokenizerFast
from transformers.models.gemma.tokenization_gemma import GemmaTokenizer
from transformers.models.siglip.configuration_siglip import SiglipVisionConfig

from liger_kernel.transformers import apply_liger_kernel_to_gemma3
Expand Down Expand Up @@ -138,7 +138,7 @@

from packaging import version
from transformers.models.gemma.configuration_gemma import GemmaConfig
from transformers.models.gemma.tokenization_gemma_fast import GemmaTokenizerFast
from transformers.models.gemma.tokenization_gemma import GemmaTokenizer
from transformers.models.gemma2.configuration_gemma2 import Gemma2Config
from transformers.models.paligemma.configuration_paligemma import PaliGemmaConfig
from transformers.models.paligemma.modeling_paligemma import PaliGemmaForConditionalGeneration
Expand Down Expand Up @@ -1020,7 +1020,7 @@ def create_processor(model_name: str):
]
)

fast_tokenizer = GemmaTokenizerFast(tokenizer_object=tokenizer_base, **tokenizer_config)
fast_tokenizer = GemmaTokenizer(tokenizer_object=tokenizer_base, **tokenizer_config)
image_processor = SiglipImageProcessor(size={"height": 224, "width": 224}, image_seq_length=256)
return PaliGemmaProcessor(image_processor=image_processor, tokenizer=fast_tokenizer)

Expand All @@ -1040,7 +1040,7 @@ def create_processor(model_name: str):
)
]
)
fast_tokenizer = GemmaTokenizerFast(tokenizer_object=tokenizer_base, **tokenizer_config)
fast_tokenizer = GemmaTokenizer(tokenizer_object=tokenizer_base, **tokenizer_config)
image_processor = Gemma3ImageProcessor()
return Gemma3Processor(image_processor=image_processor, tokenizer=fast_tokenizer)

Expand Down
6 changes: 3 additions & 3 deletions test/convergence/fp32/test_mini_models_multimodal.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@
from datasets import load_dataset
from torch.utils.data import DataLoader
from transformers import PreTrainedTokenizerFast
from transformers.models.gemma.tokenization_gemma_fast import GemmaTokenizerFast
from transformers.models.gemma.tokenization_gemma import GemmaTokenizer
from transformers.models.siglip.configuration_siglip import SiglipVisionConfig

from liger_kernel.transformers import apply_liger_kernel_to_gemma3
Expand Down Expand Up @@ -1157,7 +1157,7 @@ def create_processor(model_name: str):
)
]
)
fast_tokenizer = GemmaTokenizerFast(tokenizer_object=tokenizer_base, **tokenizer_config)
fast_tokenizer = GemmaTokenizer(tokenizer_object=tokenizer_base, **tokenizer_config)
image_processor = SiglipImageProcessor(size={"height": 224, "width": 224}, image_seq_length=256)
return PaliGemmaProcessor(image_processor=image_processor, tokenizer=fast_tokenizer)

Expand All @@ -1177,7 +1177,7 @@ def create_processor(model_name: str):
)
]
)
fast_tokenizer = GemmaTokenizerFast(tokenizer_object=tokenizer_base, **tokenizer_config)
fast_tokenizer = GemmaTokenizer(tokenizer_object=tokenizer_base, **tokenizer_config)
image_processor = Gemma3ImageProcessor()
return Gemma3Processor(image_processor=image_processor, tokenizer=fast_tokenizer)

Expand Down