Sentence Similarity
sentence-transformers
PyTorch
Transformers
English
mpnet
feature-extraction
negation
text-embeddings-inference
Instructions to use tum-nlp/NegMPNet with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use tum-nlp/NegMPNet with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("tum-nlp/NegMPNet") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use tum-nlp/NegMPNet with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("tum-nlp/NegMPNet") model = AutoModel.from_pretrained("tum-nlp/NegMPNet", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 90c0867fa1a4f24ad3f0d81167478eb46956b8ce351da882d955c623db63d7f7
- Size of remote file:
- 438 MB
- SHA256:
- cd525e47c38db18c97d9f2c5b88eb3b4a7f86416e314a6116dde2ed5a0f725b5
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.