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
Translation Task
Can these embeddings be used for translation puposes?
I.e. for detecting similar sentences in different languages? No, this model is designed for English only.
Some good options for that might be:
- https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
- https://huggingface.co/sentence-transformers/paraphrase-multilingual-mpnet-base-v2
Or searching for Sentence Transformer models with your desired language, e.g.: https://huggingface.co/models?library=sentence-transformers&language=de&sort=trending
If you want to actually do translation, you should look for translation models: https://huggingface.co/models?pipeline_tag=translation&sort=trending
@tomaarsen Thanks for replying.
I am just looking into creating my own pipeline for translation into a low resource language and was looking for text embeddings to use in my own translation pipeline. I was trying to use the embeddings using LASER3 but I was not sure how to use that.