Any example for cross-encoding?
#1
by dcalsky - opened
I used the CrossEncoder in sentence_transformers package and code is following, but the result seems not exactly as same as the result from Inference API (provided by huggingface model card).
from sentence_transformers import CrossEncoder
model = CrossEncoder('./gte-large-zh', max_length=512)
scores = model.predict([('That is a happy person', 'That is a happy dog'), ('That is a happy person', 'That is a very happy person') , ('That is a happy person', 'Today is a sunny day')], show_progress_bar=True)
print(scores)
And It also comes up some warning:
Some weights of BertForSequenceClassification were not initialized from the model checkpoint at ./gte-large-zh and are newly initialized: ['classifier.weight', 'classifier.bias']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
my result:
[0.3533868 0.41155243 0.3988041 ]
GTE is a text representation model, not a cross-encoder model structure, so CrossEncoder cannot be used to load the model.