Sentence Similarity
sentence-transformers
PyTorch
Transformers
setfit
German
bert
feature-extraction
text-embeddings-inference
Instructions to use deutsche-telekom/gbert-large-paraphrase-cosine with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use deutsche-telekom/gbert-large-paraphrase-cosine with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("deutsche-telekom/gbert-large-paraphrase-cosine") sentences = [ "Das ist eine glückliche Person", "Das ist ein glücklicher Hund", "Das ist eine sehr glückliche Person", "Heute ist ein sonniger Tag" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use deutsche-telekom/gbert-large-paraphrase-cosine with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("deutsche-telekom/gbert-large-paraphrase-cosine") model = AutoModel.from_pretrained("deutsche-telekom/gbert-large-paraphrase-cosine") - setfit
How to use deutsche-telekom/gbert-large-paraphrase-cosine with setfit:
from setfit import SetFitModel model = SetFitModel.from_pretrained("deutsche-telekom/gbert-large-paraphrase-cosine") - Inference
- Notebooks
- Google Colab
- Kaggle
Adding `safetensors` variant of this model
#2 opened over 1 year ago
by
SFconvertbot