Snowflake Arctic Embed M V1.5
S
Snowflake Arctic Embed M V1.5
Developed by Snowflake
Snowflake Arctic Embed M v1.5 is an efficient sentence embedding model, focusing on sentence similarity calculation and feature extraction tasks.
Downloads 219.46k
Release Time : 7/3/2024
Model Overview
This model is designed to generate high-quality sentence embeddings, supporting various retrieval and similarity calculation tasks, and performs well on the MTEB benchmark.
Model Features
Efficient sentence embeddings
Capable of generating high-quality sentence embeddings suitable for various similarity calculation tasks
MTEB benchmark validation
Outstanding performance on multiple MTEB benchmark datasets
Supports Transformers.js
Can be run in browser environments using Transformers.js
Model Capabilities
Sentence similarity calculation
Feature extraction
Text retrieval
Semantic search
Use Cases
Information retrieval
Q&A systems
Used to retrieve the most relevant answers to user questions
Demonstrates good retrieval performance on the CQADupstack dataset
Document similarity search
Find semantically similar documents or paragraphs
Achieved a primary score of 59.53 on the ArguAna dataset
Content recommendation
Related content recommendation
Recommend related content based on semantic similarity
🚀 snowflake-arctic-embed-m-v1.5
This is a model for sentence similarity tasks, which can be used for feature extraction and retrieval tasks. It has achieved certain results on the MTEB dataset.
📚 Documentation
Model Information
Property | Details |
---|---|
Pipeline Tag | sentence-similarity |
Tags | sentence-transformers, feature-extraction, sentence-similarity, mteb, arctic, snowflake-arctic-embed, transformers.js |
Model Type | snowflake-arctic-embed-m-v1.5 |
Task | Retrieval |
License | apache-2.0 |
Evaluation Results
MTEB ArguAna
Metric | Value |
---|---|
main_score | 59.53000000000001 |
map_at_1 | 34.282000000000004 |
map_at_10 | 50.613 |
map_at_100 | 51.269 |
map_at_1000 | 51.271 |
map_at_20 | 51.158 |
map_at_3 | 45.626 |
map_at_5 | 48.638 |
mrr_at_1 | 34.92176386913229 |
mrr_at_10 | 50.856081645555406 |
mrr_at_100 | 51.510739437069034 |
mrr_at_1000 | 51.51299498830165 |
mrr_at_20 | 51.39987941081724 |
mrr_at_3 | 45.993361782835514 |
mrr_at_5 | 48.88098624940742 |
nauc_map_at_1000_diff1 | 10.628675774160785 |
nauc_map_at_1000_max | -10.11742589992339 |
nauc_map_at_1000_std | -18.29277379812427 |
nauc_map_at_100_diff1 | 10.63250240035489 |
nauc_map_at_100_max | -10.112078786734363 |
nauc_map_at_100_std | -18.288524872706834 |
nauc_map_at_10_diff1 | 10.476494913081712 |
nauc_map_at_10_max | -9.890937746734037 |
nauc_map_at_10_std | -18.279750514750443 |
nauc_map_at_1_diff1 | 14.549204048461151 |
nauc_map_at_1_max | -12.230560087701225 |
nauc_map_at_1_std | -19.469903650130362 |
nauc_map_at_20_diff1 | 10.586564571825674 |
nauc_map_at_20_max | -10.00292720526217 |
nauc_map_at_20_std | -18.258077347878064 |
nauc_map_at_3_diff1 | 10.378663968090372 |
nauc_map_at_3_max | -10.458896171786185 |
nauc_map_at_3_std | -18.38852760333766 |
nauc_map_at_5_diff1 | 10.235960275925581 |
nauc_map_at_5_max | -10.239496080409058 |
nauc_map_at_5_std | -18.817023479445886 |
nauc_mrr_at_1000_diff1 | 8.718212649575722 |
nauc_mrr_at_1000_max | -10.81022794038691 |
nauc_mrr_at_1000_std | -17.87669499555167 |
nauc_mrr_at_100_diff1 | 8.722174171165133 |
nauc_mrr_at_100_max | -10.804840985713525 |
nauc_mrr_at_100_std | -17.872487099359986 |
nauc_mrr_at_10_diff1 | 8.609421635870238 |
nauc_mrr_at_10_max | -10.568644717548432 |
nauc_mrr_at_10_std | -17.872968762635814 |
nauc_mrr_at_1_diff1 | 12.69590006263834 |
nauc_mrr_at_1_max | -12.082056561238321 |
nauc_mrr_at_1_std | -18.036424092186657 |
nauc_mrr_at_20_diff1 | 8.684842497970315 |
nauc_mrr_at_20_max | -10.691578914627286 |
nauc_mrr_at_20_std | -17.84350301434992 |
nauc_mrr_at_3_diff1 | 8.649761557556763 |
nauc_mrr_at_3_max | -11.104694428047496 |
nauc_mrr_at_3_std | -18.149917948370344 |
nauc_mrr_at_5_diff1 | 8.433489750038396 |
nauc_mrr_at_5_max | -10.917772454397436 |
nauc_mrr_at_5_std | -18.4094211134111 |
nauc_ndcg_at_1000_diff1 | 10.19041067807956 |
nauc_ndcg_at_1000_max | -9.54328201605796 |
nauc_ndcg_at_1000_std | -17.824620427456633 |
nauc_ndcg_at_100_diff1 | 10.289491087585963 |
nauc_ndcg_at_100_max | -9.357214331420337 |
nauc_ndcg_at_100_std | -17.657600653632873 |
nauc_ndcg_at_10_diff1 | 9.435530877596092 |
nauc_ndcg_at_10_max | -8.182581635383546 |
nauc_ndcg_at_10_std | -17.603156479980388 |
nauc_ndcg_at_1_diff1 | 14.549204048461151 |
nauc_ndcg_at_1_max | -12.230560087701225 |
nauc_ndcg_at_1_std | -19.469903650130362 |
nauc_ndcg_at_20_diff1 | 9.885227087275197 |
nauc_ndcg_at_20_max | -8.52362662391439 |
nauc_ndcg_at_20_std | -17.441705436231764 |
nauc_ndcg_at_3_diff1 | 9.22542769998547 |
nauc_ndcg_at_3_max | -9.903590564219288 |
nauc_ndcg_at_3_std | -18.357220221111593 |
nauc_ndcg_at_5_diff1 | 8.8756720745828 |
nauc_ndcg_at_5_max | -9.269764943861245 |
nauc_ndcg_at_5_std | -19.009229433187784 |
nauc_precision_at_1000_diff1 | 3.733355117431035 |
nauc_precision_at_1000_max | 3.9603571352517393 |
nauc_precision_at_1000_std | 70.07345061131439 |
nauc_precision_at_100_diff1 | 29.019032142462457 |
nauc_precision_at_100_max | 40.75153328286103 |
nauc_precision_at_100_std | 62.634249549126594 |
nauc_precision_at_10_diff1 | 2.5762677254910353 |
nauc_precision_at_10_max | 6.096298633773051 |
nauc_precision_at_10_std | -11.507400451348587 |
nauc_precision_at_1_diff1 | 14.549204048461151 |
nauc_precision_at_1_max | -12.230560087701225 |
nauc_precision_at_1_std | -19.469903650130362 |
nauc_precision_at_20_diff1 | 1.715540124567996 |
nauc_precision_at_20_max | 21.53546453945913 |
nauc_precision_at_20_std | 1.537961142195571 |
nauc_precision_at_3_diff1 | 5.701850652555737 |
nauc_precision_at_3_max | -8.180345365085552 |
nauc_precision_at_3_std | -18.37033750502482 |
nauc_precision_at_5_diff1 | 3.6053552181042843 |
nauc_precision_at_5_max | -5.207647070615612 |
nauc_precision_at_5_std | -19.89491085427258 |
nauc_recall_at_1000_diff1 | 3.733355117431255 |
nauc_recall_at_1000_max | 3.9603571352482194 |
nauc_recall_at_1000_std | 70.07345061131205 |
nauc_recall_at_100_diff1 | 29.01903214246288 |
nauc_recall_at_100_max | 40.7515332828621 |
nauc_recall_at_100_std | 62.63424954912607 |
nauc_recall_at_10_diff1 | 2.5762677254911988 |
nauc_recall_at_10_max | 6.0962986337729905 |
nauc_recall_at_10_std | -11.507400451348577 |
nauc_recall_at_1_diff1 | 14.549204048461151 |
nauc_recall_at_1_max | -12.230560087701225 |
nauc_recall_at_1_std | -19.469903650130362 |
nauc_recall_at_20_diff1 | 1.7155401245682675 |
nauc_recall_at_20_max | 21.535464539459632 |
nauc_recall_at_20_std | 1.5379611421957025 |
nauc_recall_at_3_diff1 | 5.7018506525557875 |
nauc_recall_at_3_max | -8.180345365085538 |
nauc_recall_at_3_std | -18.370337505024796 |
nauc_recall_at_5_diff1 | 3.6053552181043913 |
nauc_recall_at_5_max | -5.207647070615579 |
nauc_recall_at_5_std | -19.894910854272492 |
ndcg_at_1 | 34.282000000000004 |
ndcg_at_10 | 59.53000000000001 |
ndcg_at_100 | 62.187000000000005 |
ndcg_at_1000 | 62.243 |
ndcg_at_20 | 61.451 |
ndcg_at_3 | 49.393 |
ndcg_at_5 | 54.771 |
precision_at_1 | 34.282000000000004 |
precision_at_10 | 8.791 |
precision_at_100 | 0.992 |
precision_at_1000 | 0.1 |
precision_at_20 | 4.769 |
precision_at_3 | 20.104 |
precision_at_5 | 14.651 |
recall_at_1 | 34.282000000000004 |
recall_at_10 | 87.909 |
recall_at_100 | 99.21799999999999 |
recall_at_1000 | 99.644 |
recall_at_20 | 95.377 |
recall_at_3 | 60.313 |
recall_at_5 | 73.257 |
MTEB CQADupstackAndroidRetrieval
Metric | Value |
---|---|
main_score | 53.885000000000005 |
map_at_1 | 35.429 |
map_at_10 | 47.469 |
map_at_100 | 48.997 |
map_at_1000 | 49.117 |
map_at_20 | 48.324 |
map_at_3 | 43.835 |
map_at_5 | 46.043 |
mrr_at_1 | 43.34763948497854 |
mrr_at_10 | 53.258623430297234 |
mrr_at_100 | 53.99123884299005 |
mrr_at_1000 | 54.02458101713216 |
mrr_at_20 | 53.695964669618945 |
mrr_at_3 | 50.81068192656173 |
mrr_at_5 | 52.45588936576058 |
nauc_map_at_1000_diff1 | 51.55382824218782 |
nauc_map_at_1000_max | 31.855350695084606 |
nauc_map_at_1000_std | -5.465862008150992 |
nauc_map_at_100_diff1 | 51.55889312452534 |
nauc_map_at_100_max | 31.88429637207401 |
nauc_map_at_100_std | -5.40805152544196 |
nauc_map_at_10_diff1 | 51.6592677505875 |
nauc_map_at_10_max | 31.554425233617543 |
nauc_map_at_10_std | -6.125756131339046 |
nauc_map_at_1_diff1 | 55.6889617582672 |
nauc_map_at_1_max | 27.821166966868176 |
nauc_map_at_1_std | -5.778838498211728 |
nauc_map_at_20_diff1 | 51.70520970992564 |
nauc_map_at_20_max | 31.811676633900465 |
nauc_map_at_20_std | -5.463596751904718 |
nauc_map_at_3_diff1 | 53.206169626589606 |
nauc_map_at_3_max | 31.64373830824983 |
nauc_map_at_3_std | -6.054761451312827 |
nauc_map_at_5_diff1 | 52.37308971673694 |
nauc_map_at_5_max | 31.974302019633644 |
nauc_map_at_5_std | -6.302653399940531 |
nauc_mrr_at_1000_diff1 | 49.345152231490616 |
nauc_mrr_at_1000_max | 33.49789501712511 |
nauc_mrr_at_1000_std | -6.054730861163538 |
nauc_mrr_at_100_diff1 | 49.3387577601307 |
nauc_mrr_at_100_max | 33.48149992464187 |
nauc_mrr_at_100_std | -6.061177137579308 |
nauc_mrr_at_10_diff1 | 49.08312288449718 |
nauc_mrr_at_10_max | 33.470393322577465 |
nauc_mrr_at_10_std | -6.180286430216975 |
nauc_mrr_at_1_diff1 | 52.43364978537192 |
nauc_mrr_at_1_max | 31.521755633355713 |
nauc_mrr_at_1_std | -7.002499524130836 |
nauc_mrr_at_20_diff1 | 49.311059224991766 |
nauc_mrr_at_20_max | 33.538523037692144 |
nauc_mrr_at_20_std | -6.034619474981136 |
nauc_mrr_at_3_diff1 | 49.90489868439366 |
nauc_mrr_at_3_max | 34.400493912164606 |
nauc_mrr_at_3_std | -6.028875320994629 |
nauc_mrr_at_5_diff1 | 49.033661898983475 |
nauc_mrr_at_5_max | 33.732315350193936 |
nauc_mrr_at_5_std | -6.272548556330368 |
nauc_ndcg_at_1000_diff1 | 49.81681892539247 |
nauc_ndcg_at_1000_max | 33.06518006062093 |
nauc_ndcg_at_1000_std | -4.282105713014755 |
nauc_ndcg_at_100_diff1 | 49.42362108857786 |
nauc_ndcg_at_100_max | 32. |
📄 License
This project is licensed under the apache-2.0 license.
Jina Embeddings V3
Jina Embeddings V3 is a multilingual sentence embedding model supporting over 100 languages, specializing in sentence similarity and feature extraction tasks.
Text Embedding
Transformers Supports Multiple Languages

J
jinaai
3.7M
911
Ms Marco MiniLM L6 V2
Apache-2.0
A cross-encoder model trained on the MS Marco passage ranking task for query-passage relevance scoring in information retrieval
Text Embedding English
M
cross-encoder
2.5M
86
Opensearch Neural Sparse Encoding Doc V2 Distill
Apache-2.0
A sparse retrieval model based on distillation technology, optimized for OpenSearch, supporting inference-free document encoding with improved search relevance and efficiency over V1
Text Embedding
Transformers English

O
opensearch-project
1.8M
7
Sapbert From PubMedBERT Fulltext
Apache-2.0
A biomedical entity representation model based on PubMedBERT, optimized for semantic relation capture through self-aligned pre-training
Text Embedding English
S
cambridgeltl
1.7M
49
Gte Large
MIT
GTE-Large is a powerful sentence transformer model focused on sentence similarity and text embedding tasks, excelling in multiple benchmark tests.
Text Embedding English
G
thenlper
1.5M
278
Gte Base En V1.5
Apache-2.0
GTE-base-en-v1.5 is an English sentence transformer model focused on sentence similarity tasks, excelling in multiple text embedding benchmarks.
Text Embedding
Transformers Supports Multiple Languages

G
Alibaba-NLP
1.5M
63
Gte Multilingual Base
Apache-2.0
GTE Multilingual Base is a multilingual sentence embedding model supporting over 50 languages, suitable for tasks like sentence similarity calculation.
Text Embedding
Transformers Supports Multiple Languages

G
Alibaba-NLP
1.2M
246
Polybert
polyBERT is a chemical language model designed to achieve fully machine-driven ultrafast polymer informatics. It maps PSMILES strings into 600-dimensional dense fingerprints to numerically represent polymer chemical structures.
Text Embedding
Transformers

P
kuelumbus
1.0M
5
Bert Base Turkish Cased Mean Nli Stsb Tr
Apache-2.0
A sentence embedding model based on Turkish BERT, optimized for semantic similarity tasks
Text Embedding
Transformers Other

B
emrecan
1.0M
40
GIST Small Embedding V0
MIT
A text embedding model fine-tuned based on BAAI/bge-small-en-v1.5, trained with the MEDI dataset and MTEB classification task datasets, optimized for query encoding in retrieval tasks.
Text Embedding
Safetensors English
G
avsolatorio
945.68k
29
Featured Recommended AI Models