🚀 Snowflake's Arctic-embed-l-v2.0

Snowflake's Arctic-embed-l-v2.0 is a state-of-the-art multilingual embedding model. It offers high - quality retrieval across English and multiple languages, with excellent inference efficiency and compression capabilities. It's suitable for large - scale enterprise - grade multilingual search and retrieval applications.

Model Information

GGUF quants of Snowflake/snowflake-arctic-embed-l-v2.0 created using llama.cpp

Original model card:

Snowflake's Arctic-embed-l-v2.0

News | Models | Usage | Evaluation | Contact | FAQ License | Acknowledgement

🚀 Quick Start

Snowflake arctic - embed - l - v2.0 is designed for multilingual retrieval tasks. You can quickly start using it by following the usage examples below.

✨ Features

1. Multilingual without compromise: Excels in English and non - English retrieval, outperforming leading open - source and proprietary models on benchmarks like MTEB Retrieval, CLEF, and MIRACL.
2. Inference efficiency: Its 303m non - embedding parameters inference is fast and efficient for any scale.
3. Compression - friendly: Achieves high - quality retrieval with embeddings as small as 128 bytes/vector using Matryoshka Representation Learning (MRL) and quantization - aware embedding training.
4. Drop - In Replacement: arctic - embed - l - v2.0 builds on [BAAI/bge - m3 - retromae](https://huggingface.co/BAAI/bge - m3 - retromae) which allows direct drop - in inference replacement with any form of new libraries, kernels, inference engines etc.
5. Long Context Support: arctic - embed - l - v2.0 builds on [BAAI/bge - m3 - retromae](https://huggingface.co/BAAI/bge - m3 - retromae) which can support a context window of up to 8192 via the use of RoPE.

Quality Benchmarks

Unlike most other open - source models, Arctic - embed - l - v2.0 excels across English (via MTEB Retrieval) and multilingual (via MIRACL and CLEF). All numbers mentioned below are the average NDCG@10 across the dataset being discussed.

It also delivers embeddings that are easily compressible. Leverage vector truncation via MRL to decrease vector size by 4x with less than 3% degradation in quality. Combine MRLed vectors with vector compression (Int4) to power retrieval in 128 bytes per doc.

💻 Usage Examples

Basic Usage

Using Sentence Transformers

from sentence_transformers import SentenceTransformer

# Load the model
model_name = 'Snowflake/snowflake-arctic-embed-l-v2.0'
model = SentenceTransformer(model_name)

# Define the queries and documents
queries = ['what is snowflake?', 'Where can I get the best tacos?']
documents = ['The Data Cloud!', 'Mexico City of Course!']

# Compute embeddings: use `prompt_name="query"` to encode queries!
query_embeddings = model.encode(queries, prompt_name="query") 
document_embeddings = model.encode(documents)

# Compute cosine similarity scores
scores = model.similarity(query_embeddings, document_embeddings)

# Output the results
for query, query_scores in zip(queries, scores):
    doc_score_pairs = list(zip(documents, query_scores))
    doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
    print("Query:", query)
    for document, score in doc_score_pairs:
        print(score, document)

Using Huggingface Transformers

You can use the transformers package to use Snowflake's arctic - embed model. For optimal retrieval quality, use the CLS token to embed each text portion and use the query prefix below (just on the query).

import torch
from transformers import AutoModel, AutoTokenizer

model_name = 'Snowflake/snowflake-arctic-embed-l-v2.0'
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModel.from_pretrained(model_name, add_pooling_layer=False)
model.eval()

query_prefix = 'query: '
queries  = ['what is snowflake?', 'Where can I get the best tacos?']
queries_with_prefix = ["{}{}".format(query_prefix, i) for i in queries]
query_tokens = tokenizer(queries_with_prefix, padding=True, truncation=True, return_tensors='pt', max_length=8192)

documents = ['The Data Cloud!', 'Mexico City of Course!']
document_tokens =  tokenizer(documents, padding=True, truncation=True, return_tensors='pt', max_length=8192)

# Compute token embeddings
with torch.no_grad():
    query_embeddings = model(**query_tokens)[0][:, 0]
    document_embeddings = model(**document_tokens)[0][:, 0]


# normalize embeddings
query_embeddings = torch.nn.functional.normalize(query_embeddings, p=2, dim=1)
document_embeddings = torch.nn.functional.normalize(document_embeddings, p=2, dim=1)

scores = torch.mm(query_embeddings, document_embeddings.transpose(0, 1))
for query, query_scores in zip(queries, scores):
    doc_score_pairs = list(zip(documents, query_scores))
    doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
    #Output passages & scores
    print("Query:", query)
    for document, score in doc_score_pairs:
        print(score, document)

This should produce the following scores

Query: what is snowflake?
tensor(0.2715) The Data Cloud!
tensor(0.0661) Mexico City of Course!
Query: Where can I get the best tacos?
tensor(0.2797) Mexico City of Course!
tensor(0.1250) The Data Cloud!

Using Huggingface Transformers.js

If you haven't already, you can install the Transformers.js JavaScript library from NPM using:

npm i @huggingface/transformers

You can then use the model for retrieval, as follows:

import { pipeline, dot } from '@huggingface/transformers';

// Create feature extraction pipeline
const extractor = await pipeline('feature-extraction', 'Snowflake/snowflake-arctic-embed-m-v2.0', {
    dtype: 'q8',
});

// Generate sentence embeddings
const sentences = [
    'query: what is snowflake?',
    'The Data Cloud!',
    'Mexico City of Course!',
]
const output = await extractor(sentences, { normalize: true, pooling: 'cls' });

// Compute similarity scores
const [source_embeddings, ...document_embeddings ] = output.tolist();
const similarities = document_embeddings.map(x => dot(source_embeddings, x));
console.log(similarities); // [0.24783534471401417, 0.05313122704326892]

📄 License

Arctic is licensed under the Apache 2. The released models can be used for commercial purposes free of charge.

📞 Contact

Feel free to open an issue or pull request if you have any questions or suggestions about this project. You also can email Daniel Campos(daniel.campos@snowflake.com).