Instructions to use antoinelouis/dpr-xm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use antoinelouis/dpr-xm with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("antoinelouis/dpr-xm") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Token limit and fixed prefixes ?
#2
by rjalexa - opened
Is there a token limit (context window) for the input text? Would be nice to know if I need to partition the corpus.
Also not entirely sure if the passages and the queries need a prefix pattern.
Merci beacoup !!! :)
Hey, the model's max input length is 512 tokens. No prefix required!
Thank you very much.
rjalexa changed discussion status to closed