Sentence Similarity
sentence-transformers
ONNX
Safetensors
Transformers.js
nomic_bert
feature-extraction
mteb
arctic
snowflake-arctic-embed
custom_code
Eval Results (legacy)
text-embeddings-inference
Instructions to use Snowflake/snowflake-arctic-embed-m-long with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Snowflake/snowflake-arctic-embed-m-long with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Snowflake/snowflake-arctic-embed-m-long", trust_remote_code=True) 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.js
How to use Snowflake/snowflake-arctic-embed-m-long with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('sentence-similarity', 'Snowflake/snowflake-arctic-embed-m-long'); - Notebooks
- Google Colab
- Kaggle
Model prefixes
#13
by skoulik - opened
The nomic-embed-text-v1 which the snowflake-arctic-embed-m-long is based upon requires prefixes (search_query, search_document, classification, clustering). See https://huggingface.co/nomic-ai/nomic-embed-text-v1#usage
Is the same true for snowflake-arctic-embed-m-long ?
No. It only has the prefix for queries vs docs.
spacemanidol changed discussion status to closed