Skip to content

[WWB] Fix loading the tokenizer for VLMs #2351

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
merged 1 commit into from
Jun 20, 2025
Merged

[WWB] Fix loading the tokenizer for VLMs #2351

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
2 changes: 1 addition & 1 deletion tools/who_what_benchmark/whowhatbench/text2image_evaluator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -121,7 +121,7 @@ def default_gen_image_fn(model, prompt, num_inference_steps, generator=None):
prompt,
num_inference_steps=num_inference_steps,
output_type="pil",
width=self.resolution[0],
width=self.resolution[1],
height=self.resolution[0],
generator=generator,
)
Expand Down
6 changes: 3 additions & 3 deletions tools/who_what_benchmark/whowhatbench/wwb.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -417,8 +417,8 @@ def create_evaluator(base_model, args):
seed=args.seed,
)
elif task == "visual-text":
tokenizer = load_tokenizer(args)
processor, config = load_processor(args)
tokenizer = processor.tokenizer if hasattr(processor, "tokenizer") else load_tokenizer(args)
if config and is_model_with_automatic_crop(config) and args.hf:
crop_question = False
else:
Expand Down Expand Up @@ -461,8 +461,8 @@ def create_evaluator(base_model, args):

except KeyError as e:
raise ValueError(
f"Attempted to load evaluator for '{task}', but no evaluator for this model type found!"
"Supported model types: {', '.join(EVALUATOR_REGISTRY.keys())}. Details:\n",
f"Attempted to load evaluator for '{task}', but no evaluator for this model type found! "
f"Supported model types: {', '.join(EVALUATOR_REGISTRY.keys())}. Details:\n",
e
)

Expand Down