%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
EN
Stella Large Zh V3 1792d
S
Stella Large Zh V3 1792d
Developed by dunzhang
stella-large-zh-v3-1792d is a Chinese sentence similarity calculation model based on the sentence transformer architecture, specifically designed for semantic similarity tasks involving Chinese text.
Downloads 862
Release Time : 2/17/2024
Model Overview
This model is primarily used to calculate the semantic similarity of Chinese sentences, supporting various similarity calculation methods, including cosine similarity, Euclidean distance, and Manhattan distance. It is suitable for text matching, information retrieval, and natural language understanding tasks.
Model Features
Multi-dimensional Similarity Calculation
Supports various similarity calculation methods such as cosine similarity, Euclidean distance, and Manhattan distance.
High Performance
Demonstrates excellent performance on multiple Chinese datasets, particularly achieving MAP values close to 90 in the C-MTEB/CMedQAv1 and C-MTEB/CMedQAv2 re-ranking tasks.
Broad Task Support
Not only supports sentence similarity calculation but can also be applied to various natural language processing tasks such as classification, clustering, and retrieval.
Model Capabilities
Sentence Similarity Calculation
Text Classification
Text Clustering
Information Retrieval
Re-ranking
Use Cases
Information Retrieval
Medical QA Retrieval
Used for retrieving related medical Q&A on the CMedQA dataset
MAP@10 reaches 40.14, MRR@10 reaches 48.93
Text Matching
Financial Question Matching
Used for semantic matching of financial questions on the BQ dataset
Pearson correlation of cosine similarity reaches 69.12
Text Classification
Product Review Classification
Performs review classification on the Chinese AmazonReviews dataset
Accuracy reaches 46.32
🚀 stella-large-zh-v3-1792d
This model is designed for sentence - similarity tasks, with excellent performance in multiple datasets of the C - MTEB and MTEB benchmarks.
📚 Documentation
Model Information
| Property | Details |
|---|---|
| Pipeline Tag | sentence - similarity |
| Tags | sentence - transformers, feature - extraction, sentence - similarity, mteb |
| Model Name | stella - large - zh - v3 - 1792d |
Performance Results
1. STS Task
| Dataset | Metric Type | Value |
|---|---|---|
| C - MTEB/AFQMC (validation) | cos_sim_pearson | 54.48093298255762 |
| C - MTEB/AFQMC (validation) | cos_sim_spearman | 59.105354109068685 |
| C - MTEB/AFQMC (validation) | euclidean_pearson | 57.761189988643444 |
| C - MTEB/AFQMC (validation) | euclidean_spearman | 59.10537421115596 |
| C - MTEB/AFQMC (validation) | manhattan_pearson | 56.94359297051431 |
| C - MTEB/AFQMC (validation) | manhattan_spearman | 58.37611109821567 |
| C - MTEB/ATEC (test) | cos_sim_pearson | 54.39711127600595 |
| C - MTEB/ATEC (test) | cos_sim_spearman | 58.190191920824454 |
| C - MTEB/ATEC (test) | euclidean_pearson | 61.80082379352729 |
| C - MTEB/ATEC (test) | euclidean_spearman | 58.19018966860797 |
| C - MTEB/ATEC (test) | manhattan_pearson | 60.927601060396206 |
| C - MTEB/ATEC (test) | manhattan_spearman | 57.78832902694192 |
| C - MTEB/BQ (test) | cos_sim_pearson | 69.12211326097868 |
| C - MTEB/BQ (test) | cos_sim_spearman | 71.0741302039443 |
| C - MTEB/BQ (test) | euclidean_pearson | 69.89070483887852 |
| C - MTEB/BQ (test) | euclidean_spearman | 71.07413020351787 |
| C - MTEB/BQ (test) | manhattan_pearson | 69.62345441260962 |
| C - MTEB/BQ (test) | manhattan_spearman | 70.8517591280618 |
2. Classification Task
| Dataset | Metric Type | Value |
|---|---|---|
| mteb/amazon_reviews_multi (test, zh) | accuracy | 46.31600000000001 |
| mteb/amazon_reviews_multi (test, zh) | f1 | 44.45281663598873 |
3. Clustering Task
| Dataset | Metric Type | Value |
|---|---|---|
| C - MTEB/CLSClusteringP2P (test) | v_measure | 41.937723608805314 |
| C - MTEB/CLSClusteringS2S (test) | v_measure | 40.34373057675427 |
4. Reranking Task
| Dataset | Metric Type | Value |
|---|---|---|
| C - MTEB/CMedQAv1 - reranking (test) | map | 88.98896401788376 |
| C - MTEB/CMedQAv1 - reranking (test) | mrr | 90.97119047619047 |
| C - MTEB/CMedQAv2 - reranking (test) | map | 89.59718540244556 |
| C - MTEB/CMedQAv2 - reranking (test) | mrr | 91.41246031746032 |
5. Retrieval Task
| Dataset | Metric Type | Value |
|---|---|---|
| C - MTEB/CmedqaRetrieval (dev) | map_at_1 | 26.954 |
| C - MTEB/CmedqaRetrieval (dev) | map_at_10 | 40.144999999999996 |
| C - MTEB/CmedqaRetrieval (dev) | map_at_100 | 42.083999999999996 |
| C - MTEB/CmedqaRetrieval (dev) | map_at_1000 | 42.181000000000004 |
| C - MTEB/CmedqaRetrieval (dev) | map_at_3 | 35.709 |
| C - MTEB/CmedqaRetrieval (dev) | map_at_5 | 38.141000000000005 |
| C - MTEB/CmedqaRetrieval (dev) | mrr_at_1 | 40.71 |
| C - MTEB/CmedqaRetrieval (dev) | mrr_at_10 | 48.93 |
| C - MTEB/CmedqaRetrieval (dev) | mrr_at_100 | 49.921 |
| C - MTEB/CmedqaRetrieval (dev) | mrr_at_1000 | 49.958999999999996 |
| C - MTEB/CmedqaRetrieval (dev) | mrr_at_3 | 46.32 |
| C - MTEB/CmedqaRetrieval (dev) | mrr_at_5 | 47.769 |
| C - MTEB/CmedqaRetrieval (dev) | ndcg_at_1 | 40.71 |
| C - MTEB/CmedqaRetrieval (dev) | ndcg_at_10 | 46.869 |
| C - MTEB/CmedqaRetrieval (dev) | ndcg_at_100 | 54.234 |
| C - MTEB/CmedqaRetrieval (dev) | ndcg_at_1000 | 55.854000000000006 |
| C - MTEB/CmedqaRetrieval (dev) | ndcg_at_3 | 41.339 |
| C - MTEB/CmedqaRetrieval (dev) | ndcg_at_5 | 43.594 |
| C - MTEB/CmedqaRetrieval (dev) | precision_at_1 | 40.71 |
| C - MTEB/CmedqaRetrieval (dev) | precision_at_10 | 10.408000000000001 |
| C - MTEB/CmedqaRetrieval (dev) | precision_at_100 | 1.635 |
| C - MTEB/CmedqaRetrieval (dev) | precision_at_1000 | 0.184 |
| C - MTEB/CmedqaRetrieval (dev) | precision_at_3 | 23.348 |
| C - MTEB/CmedqaRetrieval (dev) | precision_at_5 | 16.929 |
| C - MTEB/CmedqaRetrieval (dev) | recall_at_1 | 26.954 |
| C - MTEB/CmedqaRetrieval (dev) | recall_at_10 | 57.821999999999996 |
| C - MTEB/CmedqaRetrieval (dev) | recall_at_100 | 88.08200000000001 |
| C - MTEB/CmedqaRetrieval (dev) | recall_at_1000 | 98.83800000000001 |
| C - MTEB/CmedqaRetrieval (dev) | recall_at_3 | 41.221999999999994 |
| C - MTEB/CmedqaRetrieval (dev) | recall_at_5 | 48.241 |
| C - MTEB/CovidRetrieval (dev) | map_at_1 | 69.705 |
| C - MTEB/CovidRetrieval (dev) | map_at_10 | 78.648 |
| C - MTEB/CovidRetrieval (dev) | map_at_100 | 78.888 |
| C - MTEB/CovidRetrieval (dev) | map_at_1000 | 78.89399999999999 |
| C - MTEB/CovidRetrieval (dev) | map_at_3 | 77.151 |
| C - MTEB/CovidRetrieval (dev) | map_at_5 | 77.98 |
| C - MTEB/CovidRetrieval (dev) | mrr_at_1 | 69.863 |
| C - MTEB/CovidRetrieval (dev) | mrr_at_10 | 78.62599999999999 |
| C - MTEB/CovidRetrieval (dev) | mrr_at_100 | 78.861 |
| C - MTEB/CovidRetrieval (dev) | mrr_at_1000 | 78.867 |
| C - MTEB/CovidRetrieval (dev) | mrr_at_3 | 77.204 |
| C - MTEB/CovidRetrieval (dev) | mrr_at_5 | 78.005 |
| C - MTEB/CovidRetrieval (dev) | ndcg_at_1 | 69.968 |
| C - MTEB/CovidRetrieval (dev) | ndcg_at_10 | 82.44399999999999 |
| C - MTEB/CovidRetrieval (dev) | ndcg_at_100 | 83.499 |
| C - MTEB/CovidRetrieval (dev) | ndcg_at_1000 | 83.647 |
| C - MTEB/CovidRetrieval (dev) | ndcg_at_3 | 79.393 |
| C - MTEB/CovidRetrieval (dev) | ndcg_at_5 | 80.855 |
| C - MTEB/CovidRetrieval (dev) | precision_at_1 | 69.968 |
| C - MTEB/CovidRetrieval (dev) | precision_at_10 | 9.515 |
| C - MTEB/CovidRetrieval (dev) | precision_at_100 | 0.9990000000000001 |
| C - MTEB/CovidRetrieval (dev) | precision_at_1000 | 0.101 |
| C - MTEB/CovidRetrieval (dev) | precision_at_3 | 28.802 |
| C - MTEB/CovidRetrieval (dev) | precision_at_5 | 18.019 |
| C - MTEB/CovidRetrieval (dev) | recall_at_1 | 69.705 |
| C - MTEB/CovidRetrieval (dev) | recall_at_10 | 94.152 |
| C - MTEB/CovidRetrieval (dev) | recall_at_100 | 98.84100000000001 |
| C - MTEB/CovidRetrieval (dev) | recall_at_1000 | 100.0 |
| C - MTEB/CovidRetrieval (dev) | recall_at_3 | 85.774 |
| C - MTEB/CovidRetrieval (dev) | recall_at_5 | 89.252 |
| C - MTEB/DuRetrieval (dev) | map_at_1 | 25.88 |
| C - MTEB/DuRetrieval (dev) | map_at_10 | 79.857 |
| C - MTEB/DuRetrieval (dev) | map_at_100 | 82.636 |
| C - MTEB/DuRetrieval (dev) | map_at_1000 | 82.672 |
| C - MTEB/DuRetrieval (dev) | map_at_3 | 55.184 |
| C - MTEB/DuRetrieval (dev) | map_at_5 | 70.009 |
| C - MTEB/DuRetrieval (dev) | mrr_at_1 | 89.64999999999999 |
| C - MTEB/DuRetrieval (dev) | mrr_at_10 | 92.967 |
| C - MTEB/DuRetrieval (dev) | mrr_at_100 | 93.039 |
| C - MTEB/DuRetrieval (dev) | mrr_at_1000 | 93.041 |
| C - MTEB/DuRetrieval (dev) | mrr_at_3 | 92.65 |
| C - MTEB/DuRetrieval (dev) | mrr_at_5 | 92.86 |
| C - MTEB/DuRetrieval (dev) | ndcg_at_1 | 89.64999999999999 |
| C - MTEB/DuRetrieval (dev) | ndcg_at_10 | 87.126 |
| C - MTEB/DuRetrieval (dev) | ndcg_at_100 | 89.898 |
| C - MTEB/DuRetrieval (dev) | ndcg_at_1000 | 90.253 |
| C - MTEB/DuRetrieval (dev) | ndcg_at_3 | 86.012 |
| C - MTEB/DuRetrieval (dev) | ndcg_at_5 | 85.124 |
| C - MTEB/DuRetrieval (dev) | precision_at_1 | 89.64999999999999 |
| C - MTEB/DuRetrieval (dev) | precision_at_10 | 41.735 |
| C - MTEB/DuRetrieval (dev) | precision_at_100 | 4.797 |
| C - MTEB/DuRetrieval (dev) | precision_at_1000 | 0.488 |
| C - MTEB/DuRetrieval (dev) | precision_at_3 | 77.267 |
| C - MTEB/DuRetrieval (dev) | precision_at_5 | 65.48 |
| C - MTEB/DuRetrieval (dev) | recall_at_1 | 25.88 |
| C - MTEB/DuRetrieval (dev) | recall_at_10 | 88.28399999999999 |
| C - MTEB/DuRetrieval (dev) | recall_at_100 | 97.407 |
| C - MTEB/DuRetrieval (dev) | recall_at_1000 | 99.29299999999999 |
| C - MTEB/DuRetrieval (dev) | recall_at_3 | 57.38799999999999 |
| C - MTEB/DuRetrieval (dev) | recall_at_5 | 74.736 |
| C - MTEB/EcomRetrieval (dev) | map_at_1 | 53.2 |
| C - MTEB/EcomRetrieval (dev) | map_at_10 | 63.556000000000004 |
| C - MTEB/EcomRetrieval (dev) | map_at_100 | 64.033 |
| C - MTEB/EcomRetrieval (dev) | map_at_1000 | 64.044 |
| C - MTEB/EcomRetrieval (dev) | map_at_3 | 60.983 |
| C - MTEB/EcomRetrieval (dev) | map_at_5 | 62.588 |
| C - MTEB/EcomRetrieval (dev) | mrr_at_1 | 53.2 |
| C - MTEB/EcomRetrieval (dev) | mrr_at_10 | 63.556000000000004 |
| C - MTEB/EcomRetrieval (dev) | mrr_at_100 | 64.033 |
| C - MTEB/EcomRetrieval (dev) | mrr_at_1000 | 64.044 |
| C - MTEB/EcomRetrieval (dev) | mrr_at_3 | 60.983 |
| C - MTEB/EcomRetrieval (dev) | mrr_at_5 | 62.588 |
| C - MTEB/EcomRetrieval (dev) | ndcg_at_1 | 53.2 |
| C - MTEB/EcomRetrieval (dev) | ndcg_at_10 | 68.61699999999999 |
| C - MTEB/EcomRetrieval (dev) | ndcg_at_100 | 70.88499999999999 |
| C - MTEB/EcomRetrieval (dev) | ndcg_at_1000 | 71.15899999999999 |
| C - MTEB/EcomRetrieval (dev) | ndcg_at_3 | 63.434000000000005 |
| C - MTEB/EcomRetrieval (dev) | ndcg_at_5 | 66.301 |
| C - MTEB/EcomRetrieval (dev) | precision_at_1 | 53.2 |
| C - MTEB/EcomRetrieval (dev) | precision_at_10 | 8.450000000000001 |
| C - MTEB/EcomRetrieval (dev) | precision_at_100 | 0.95 |
| C - MTEB/EcomRetrieval (dev) | precision_at_1000 | 0.097 |
6. PairClassification Task
| Dataset | Metric Type | Value |
|---|---|---|
| C - MTEB/CMNLI (validation) | cos_sim_accuracy | 83.6680697534576 |
| C - MTEB/CMNLI (validation) | cos_sim_ap | 90.77401562455269 |
| C - MTEB/CMNLI (validation) | cos_sim_f1 | 84.68266427450101 |
| C - MTEB/CMNLI (validation) | cos_sim_precision | 81.36177547942253 |
| C - MTEB/CMNLI (validation) | cos_sim_recall | 88.28618190320317 |
| C - MTEB/CMNLI (validation) | dot_accuracy | 83.6680697534576 |
| C - MTEB/CMNLI (validation) | dot_ap | 90.76429465198817 |
| C - MTEB/CMNLI (validation) | dot_f1 | 84.68266427450101 |
| C - MTEB/CMNLI (validation) | dot_precision | 81.36177547942253 |
| C - MTEB/CMNLI (validation) | dot_recall | 88.28618190320317 |
| C - MTEB/CMNLI (validation) | euclidean_accuracy | 83.6680697534576 |
| C - MTEB/CMNLI (validation) | euclidean_ap | 90.77401909305344 |
| C - MTEB/CMNLI (validation) | euclidean_f1 | 84.68266427450101 |
| C - MTEB/CMNLI (validation) | euclidean_precision | 81.36177547942253 |
| C - MTEB/CMNLI (validation) | euclidean_recall | 88.28618190320317 |
| C - MTEB/CMNLI (validation) | manhattan_accuracy | 83.40348767288035 |
| C - MTEB/CMNLI (validation) | manhattan_ap | 90.57002020310819 |
| C - MTEB/CMNLI (validation) | manhattan_f1 | 84.51526032315978 |
| C - MTEB/CMNLI (validation) | manhattan_precision | 81.25134843581445 |
| C - MTEB/CMNLI (validation) | manhattan_recall | 88.05237315875614 |
| C - MTEB/CMNLI (validation) | max_accuracy | 83.6680697534576 |
| C - MTEB/CMNLI (validation) | max_ap | 90.77401909305344 |
| C - MTEB/CMNLI (validation) | max_f1 | 84.68266427450101 |
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
Transformers Supports Multiple LanguagesJ
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
Transformers EnglishO
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
Transformers Supports Multiple LanguagesG
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
Transformers Supports Multiple LanguagesG
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
TransformersP
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
Transformers OtherB
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
Safetensors EnglishG
avsolatorio
945.68k
29
Featured Recommended AI Models