Model reference · open weights
snowflake-arctic-embed-l is an open-weight embedding model from Snowflake, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
News - 12/11/2024: Release of Technical Report - 12/04/2024: Release of snowflake-arctic-embed-l-v2.0 and snowflake-arctic-embed-m-v2.0 our newest models with multilingual workloads in mind. Models Snowflake arctic-embed-l-v2.0 is the newest addition to the suite of embedding models Snowflake has released optimizing for retrieval performance and inference efficiency. Arctic Embed 2.0 introduces a new standard for multilingual embedding models, combining high-quality multilingual text retrieval without sacrificing performance in English. Released under the permissive Apache 2.0 license, Arctic Embed 2.0 is ideal for applications that demand reliable, enterprise-grade multilingual search and retrieval at scale. Key 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. Please note that like our v1.5 model, the MRL for this model is 256 dimensions, and high-quality 128-byte compression is achieved via 4-bit quantization (e.g. using a pq256x4fs fast-scan FAISS index or using the example code published alongside our 1.5 model). 4. Drop-In Replacement: arctic-embed-l-v2.0 builds on 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 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). You no longer need to support models to empower high-quality English and multilingual retrieval. All numbers mentioned below are the average NDCG@10 across the dataset being discussed. Aside from high-quality retrieval arc
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | Snowflake |
|---|---|
| Type | Embedding models |
| Parameters (lead) | 568M |
| Context | 8,194 tokens |
| Variants | 2 |
| Runs with | sentence-transformers |
| Released | 2024-11-08 |
| Popularity | 715k downloads / month |
| Likes | 251 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
Benchmarks
As published on the model card — the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| Classification | MTEB AmazonCounterfactualClassification (en-ext) | accuracy | 67.039 |
| Classification | MTEB AmazonCounterfactualClassification (en-ext) | f1 | 55.181 |
| Classification | MTEB AmazonCounterfactualClassification (en-ext) | f1_weighted | 73.411 |
| Classification | MTEB AmazonCounterfactualClassification (en-ext) | ap | 17.991 |
| Classification | MTEB AmazonCounterfactualClassification (en-ext) | ap_weighted | 17.991 |
| Classification | MTEB AmazonCounterfactualClassification (en-ext) | main_score | 67.039 |
| Classification | MTEB AmazonCounterfactualClassification (en) | accuracy | 65.597 |
| Classification | MTEB AmazonCounterfactualClassification (en) | f1 | 60.244 |
| Classification | MTEB AmazonCounterfactualClassification (en) | f1_weighted | 68.998 |
| Classification | MTEB AmazonCounterfactualClassification (en) | ap | 29.762 |
| Classification | MTEB AmazonCounterfactualClassification (en) | ap_weighted | 29.762 |
| Classification | MTEB AmazonCounterfactualClassification (en) | main_score | 65.597 |
| Classification | MTEB AmazonPolarityClassification (default) | accuracy | 74.257 |
| Classification | MTEB AmazonPolarityClassification (default) | f1 | 74.029 |
| Classification | MTEB AmazonPolarityClassification (default) | f1_weighted | 74.029 |
| Classification | MTEB AmazonPolarityClassification (default) | ap | 68.76 |
| Classification | MTEB AmazonPolarityClassification (default) | ap_weighted | 68.76 |
| Classification | MTEB AmazonPolarityClassification (default) | main_score | 74.257 |
| Classification | MTEB AmazonReviewsClassification (en) | accuracy | 34.946 |
| Classification | MTEB AmazonReviewsClassification (en) | f1 | 34.285 |
| Classification | MTEB AmazonReviewsClassification (en) | f1_weighted | 34.285 |
| Classification | MTEB AmazonReviewsClassification (en) | main_score | 34.946 |
| Retrieval | MTEB ArguAna (default) | ndcg_at_1 | 33.286 |
| Retrieval | MTEB ArguAna (default) | ndcg_at_3 | 49.051 |
Using it via the API
Once AxForge deploys snowflake-arctic-embed-l for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (snowflake-arctic-embed-l below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/embeddings \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"snowflake-arctic-embed-l","input":"text to embed"}'
Details
Languages
Tags
Papers
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗
Explore