Sentence Similarity
sentence-transformers
ONNX
Safetensors
Transformers.js
xlm-roberta
feature-extraction
mteb
arctic
snowflake-arctic-embed
Eval Results (legacy)
Eval Results
text-embeddings-inference
Instructions to use Snowflake/snowflake-arctic-embed-l-v2.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use Snowflake/snowflake-arctic-embed-l-v2.0 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("Snowflake/snowflake-arctic-embed-l-v2.0") 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] - Transformers.js
How to use Snowflake/snowflake-arctic-embed-l-v2.0 with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('sentence-similarity', 'Snowflake/snowflake-arctic-embed-l-v2.0'); - Inference
- Notebooks
- Google Colab
- Kaggle
what's the purpose of "prompt_name=query"?
#7
by samwu66 - opened
what's the purpose of "prompt_name=query"?
It breaks the symmetry of encoding queries and documents (which are often different in form) into the same embedding space.
Here's a reference if you're curious to read more: https://arxiv.org/abs/2212.03533 (section 4.1)
Got it, thanks a lot!
lukemerrick changed discussion status to closed