Instructions to use TencentBAC/Conan-embedding-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use TencentBAC/Conan-embedding-v1 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("TencentBAC/Conan-embedding-v1") 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
what is the maximum token number supported by Conan model?
#1
by wenjun2222 - opened
thx!
The maximum input token num supported by the Conan-embedding-v1 is 512.
Subsequent versions of the Conan-embedding will support longer inputs.
Vurkty changed discussion status to closed