Instructions to use sentence-transformers/all-mpnet-base-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use sentence-transformers/all-mpnet-base-v2 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("sentence-transformers/all-mpnet-base-v2") 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 sentence-transformers/all-mpnet-base-v2 with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("sentence-transformers/all-mpnet-base-v2") model = AutoModelForMaskedLM.from_pretrained("sentence-transformers/all-mpnet-base-v2") - Inference
- Notebooks
- Google Colab
- Kaggle
How to compare sentences?
Is there a more advanced way to compare vectorised sentences than just with cosine/euclidean? It seems like there are transformer options which do that and it can only be done by fine-tuning and changing the target?
Did you figure this out?
Sadly, no
With this model, comparing vectors can only be done using cosine similarity/dot score/euclidean distance. If you want to use the attention mechanism from transformer models, then you might be interested in cross-encoder models: https://huggingface.co/cross-encoder, https://huggingface.co/BAAI/bge-reranker-base, https://huggingface.co/mixedbread-ai/mxbai-rerank-base-v1
- Tom Aarsen