Instructions to use NoesisLab/Collins-Embedding-3M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use NoesisLab/Collins-Embedding-3M with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("NoesisLab/Collins-Embedding-3M") 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] - Notebooks
- Google Colab
- Kaggle
Download collins_sts_comparison.png from NoesisLab/Collins-Embedding-3M: direct link, hf CLI and curl.
- Browser
- Download file 350 kB
-
https://huggingface.co/NoesisLab/Collins-Embedding-3M/resolve/main/collins_sts_comparison.png
- Command line
-
hf download hf://NoesisLab/Collins-Embedding-3M/collins_sts_comparison.png
-
curl -L -o collins_sts_comparison.png https://huggingface.co/NoesisLab/Collins-Embedding-3M/resolve/main/collins_sts_comparison.png
350 kB

- Xet hash:
- 6facb1f1cbb748cfbbd9492ccae3085e5630e87b4efbbffcc7668b0102b0f639
- Size of remote file:
- 350 kB
- SHA256:
- c083c7a9ea4fe4b0f8fd10fe54d0b5a1a3eee13f4cdb6e743a0fac4e57af3879
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.