Instructions to use Alibaba-NLP/gte-multilingual-reranker-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Alibaba-NLP/gte-multilingual-reranker-base with sentence-transformers:
from sentence_transformers import CrossEncoder model = CrossEncoder("Alibaba-NLP/gte-multilingual-reranker-base", trust_remote_code=True) query = "Which planet is known as the Red Planet?" passages = [ "Venus is often called Earth's twin because of its similar size and proximity.", "Mars, known for its reddish appearance, is often referred to as the Red Planet.", "Jupiter, the largest planet in our solar system, has a prominent red spot.", "Saturn, famous for its rings, is sometimes mistaken for the Red Planet." ] scores = model.predict([(query, passage) for passage in passages]) print(scores) - Transformers
How to use Alibaba-NLP/gte-multilingual-reranker-base with Transformers:
# Load model directly from transformers import AutoModelForSequenceClassification model = AutoModelForSequenceClassification.from_pretrained("Alibaba-NLP/gte-multilingual-reranker-base", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
metadata is None
python 3.10
transformers==4.46.2
torch==2.5.1
safetensors==0.4.5
venv/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:559, in _BaseAutoModelClass.from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs)
557 cls.register(config.class, model_class, exist_ok=True)
558 model_class = add_generation_mixin_to_remote_model(model_class)
--> 559 return model_class.from_pretrained(
560 pretrained_model_name_or_path, *model_args, config=config, **hub_kwargs, **kwargs
561 )
562 elif type(config) in cls._model_mapping.keys():
563 model_class = _get_model_class(config, cls._model_mapping)
venv/lib/python3.10/site-packages/transformers/modeling_utils.py:3997, in PreTrainedModel.from_pretrained(cls, pretrained_model_name_or_path, config, cache_dir, ignore_mismatched_sizes, force_download, local_files_only, token, revision, use_safetensors, weights_only, *model_args, **kwargs)
3994 with safe_open(resolved_archive_file, framework="pt") as f:
3995 metadata = f.metadata()
-> 3997 if metadata.get("format") == "pt":
3998 pass
3999 elif metadata.get("format") == "tf":
AttributeError: 'NoneType' object has no attribute 'get'
I am having the same issue:
File "\Lib\site-packages\transformers\models\auto\auto_factory.py", line 559, in from_pretrained
return model_class.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "\Lib\site-packages\transformers\modeling_utils.py", line 3738, in from_pretrained
if metadata.get("format") == "pt":
^^^^^^^^^^^^
AttributeError: 'NoneType' object has no attribute 'get'
seems the latest model has something wrong.
I can use the previous one without problem https://hf-mirror.com/Alibaba-NLP/gte-multilingual-reranker-base/tree/4e88bd5dec38b6b9a7e623755029fc124c319d67
model_name_or_path = "Alibaba-NLP/gte-multilingual-reranker-base"
revision = "4e88bd5dec38b6b9a7e623755029fc124c319d67"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForSequenceClassification.from_pretrained(
model_name_or_path, trust_remote_code=True,
torch_dtype=torch.float16,
revision=revision
)
The main branch file has been updated to fix this problem.