GLiNERClassifier raises AttributeError: 'UniEncoderTokenGLiNER' object has no attribute 'run'

[birdalugur]

Description

The text classification example from the documentation fails with an AttributeError when calling GLiNERClassifier.

Documentation example:

from gliner import GLiNER
from gliner.multitask import GLiNERClassifier

# Initialize
model = GLiNER.from_pretrained("knowledgator/gliner-multitask-large-v0.5")
classifier = GLiNERClassifier(model=model)

# Single-label classification
text = "SpaceX successfully launched a new rocket into orbit."
labels = ['science', 'technology', 'business', 'sports']

predictions = classifier(text, classes=labels, multi_label=False)
print(predictions)

Error

AttributeError: 'UniEncoderTokenGLiNER' object has no attribute 'run'

Full traceback:

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
/tmp/ipykernel_707/4252357861.py in <cell line: 0>()
----> 1 predictions = classifier(text, classes=labels, multi_label=False)
      2 print(predictions)

1 frames
/usr/local/lib/python3.12/dist-packages/torch/nn/modules/module.py in __getattr__(self, name)
   1966             if name in modules:
   1967                 return modules[name]
-> 1968         raise AttributeError(
   1969             f"'{type(self).__name__}' object has no attribute '{name}'"
   1970         )

AttributeError: 'UniEncoderTokenGLiNER' object has no attribute 'run'

Environment

• Python: 3.12
• GLiNER version: 0.2.26

Steps to Reproduce

ˋˋˋ
! pip install tiktoken
! pip install sentencepiece protobuf
! pip install gliner[gpu]
! pip install -U langchain-text-splitters
! pip install evaluate
! pip install flashdeberta -U
ˋˋˋ

from gliner import GLiNER
from gliner.multitask import GLiNERClassifier

model = GLiNER.from_pretrained("knowledgator/gliner-multitask-large-v0.5")
classifier = GLiNERClassifier(model=model)

text = "SpaceX successfully launched a new rocket into orbit."
labels = ['science', 'technology', 'business', 'sports']

predictions = classifier(text, classes=labels, multi_label=False)

Expected Behavior

The classifier should return a prediction similar to the documentation example.

[Ingvarstep]

@birdalugur, thanks for raising this issue, it happens because the inference method was renamed from run to inference. We will fix it in the next release.