%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
Dmeta Embedding Zh Small
D
Dmeta Embedding Zh Small
Developed by DMetaSoul
Dmeta-embedding-zh-small is a model that performs excellently in multiple natural language processing tasks and is particularly suitable for Chinese text processing.
Downloads 10.76k
Release Time : 3/25/2024
Model Overview
This model performs outstandingly in tasks such as semantic text similarity, classification, clustering, reordering, and retrieval, and is suitable for generating embedding representations of Chinese texts.
Model Features
Excellent multi-task performance
Performs outstandingly in various natural language processing tasks, including semantic similarity calculation and text classification.
Optimized for Chinese
Specifically optimized for Chinese texts and performs excellently on Chinese datasets.
Efficient retrieval ability
Demonstrates efficient performance in retrieval tasks and is suitable for building Chinese search engines or question-answering systems.
Model Capabilities
Semantic text similarity calculation
Text classification
Text clustering
Retrieval result reordering
Information retrieval
Use Cases
Search engine
Chinese web page retrieval
Used as the core embedding model for building a Chinese web page search engine.
The map@10 reaches 35.952 on the C-MTEB/CmedqaRetrieval dataset.
Question-answering system
Medical question-answering retrieval
Used for answer retrieval in medical question-answering systems.
The mrr reaches 88.799 on the C-MTEB/CMedQAv1-reranking task.
E-commerce application
Product review classification
Used for sentiment analysis and classification of product reviews on e-commerce platforms.
The accuracy reaches 85.572 on the C-MTEB/JDReview-classification task.
🚀 Dmeta-embedding-zh-small
Dmeta-embedding-zh-small is a model with performance metrics on various tasks in the MTEB benchmark, including semantic text similarity, classification, clustering, reranking, retrieval, and pair classification.
📚 Documentation
Model Information
| Property | Details |
|---|---|
| Model Name | Dmeta-embedding-zh-small |
| Tags | mteb |
Task Performance Metrics
1. STS (Semantic Textual Similarity)
-
C-MTEB/AFQMC (Validation Split)
Metric Value cos_sim_pearson 55.38441014851534 cos_sim_spearman 59.54284362578262 euclidean_pearson 58.18592108890414 euclidean_spearman 59.54284362133902 manhattan_pearson 58.142197046175916 manhattan_spearman 59.47943468645265 -
C-MTEB/ATEC (Test Split)
Metric Value cos_sim_pearson 55.96911621560259 cos_sim_spearman 58.6334496101353 euclidean_pearson 62.78426382809823 euclidean_spearman 58.63344961011331 manhattan_pearson 62.80625401678188 manhattan_spearman 58.618722128260394 -
C-MTEB/BQ (Test Split)
Metric Value cos_sim_pearson 68.56815521242152 cos_sim_spearman 70.30776353631751 euclidean_pearson 69.10087719019191 euclidean_spearman 70.30775660748148 manhattan_pearson 69.0672710967445 manhattan_spearman 70.31940638148254 -
C-MTEB/LCQMC (Test Split)
Metric Value cos_sim_pearson 73.03085269274996 cos_sim_spearman 78.72837937949888 euclidean_pearson 78.34911745798928 euclidean_spearman 78.72838602779268 manhattan_pearson 78.31833697617105 manhattan_spearman 78.69603741566397 -
mteb/sts22-crosslingual-sts (zh, Test Split)
Metric Value cos_sim_pearson 66.47464607633356 cos_sim_spearman 66.76311382148693 euclidean_pearson 67.25180409604143 euclidean_spearman 66.76311382148693 manhattan_pearson 67.6928257682864 manhattan_spearman 67.08172581019826 -
C-MTEB/PAWSX (Test Split)
Metric Value cos_sim_pearson 38.5692290188029 cos_sim_spearman 42.965264868554335 euclidean_pearson 43.002526263615735 euclidean_spearman 42.97561576045246 manhattan_pearson 43.050089639788936 manhattan_spearman 43.038497558804934 -
C-MTEB/QBQTC (Test Split)
Metric Value cos_sim_pearson 38.99284895602663 cos_sim_spearman 41.02655813481606 euclidean_pearson 38.934953519378354 euclidean_spearman 41.02680077136343 manhattan_pearson 39.224809609807785 manhattan_spearman 41.13950779185706 -
C-MTEB/STSB (Test Split)
Metric Value cos_sim_pearson [To be filled if available] cos_sim_spearman [To be filled if available] euclidean_pearson [To be filled if available] euclidean_spearman [To be filled if available] manhattan_pearson [To be filled if available] manhattan_spearman [To be filled if available]
2. Classification
-
mteb/amazon_reviews_multi (zh, Test Split)
Metric Value accuracy 44.88 f1 42.739249460584375 -
C-MTEB/IFlyTek-classification (Validation Split)
Metric Value accuracy 49.111196614082345 f1 37.07930546974089 -
C-MTEB/JDReview-classification (Test Split)
Metric Value accuracy 85.57223264540339 ap 53.30690968994808 f1 80.20587062271773 -
mteb/amazon_massive_intent (zh-CN, Test Split)
Metric Value accuracy 70.78345662407531 f1 68.35683436974351 -
mteb/amazon_massive_scenario (zh-CN, Test Split)
Metric Value accuracy 73.16408876933423 f1 73.31484873459382 -
C-MTEB/MultilingualSentiment-classification (Validation Split)
Metric Value accuracy 74.38999999999999 f1 74.07161306140839 -
C-MTEB/OnlineShopping-classification (Test Split)
Metric Value accuracy 93.12000000000002 ap 91.0749103088623 f1 93.10837266607813
3. Clustering
-
C-MTEB/CLSClusteringP2P (Test Split)
Metric Value v_measure 40.7861976704356 -
C-MTEB/CLSClusteringS2S (Test Split)
Metric Value v_measure 38.43028280281822
4. Reranking
-
C-MTEB/CMedQAv1-reranking (Test Split)
Metric Value map 86.78386695617407 mrr 88.79857142857142 -
C-MTEB/CMedQAv2-reranking (Test Split)
Metric Value map 87.38582377194436 mrr 89.17158730158731 -
C-MTEB/Mmarco-reranking (Dev Split)
Metric Value map 27.391692468538416 mrr 26.44682539682539
5. Retrieval
-
C-MTEB/CmedqaRetrieval (Dev Split)
Metric Value map_at_1 23.746000000000002 map_at_10 35.952 map_at_100 37.946999999999996 map_at_1000 38.059 map_at_3 31.680999999999997 map_at_5 34.046 mrr_at_1 36.409000000000006 mrr_at_10 44.801 mrr_at_100 45.842 mrr_at_1000 45.885999999999996 mrr_at_3 42.081 mrr_at_5 43.613 ndcg_at_1 36.409000000000006 ndcg_at_10 42.687000000000005 ndcg_at_100 50.352 ndcg_at_1000 52.275000000000006 ndcg_at_3 37.113 ndcg_at_5 39.434000000000005 precision_at_1 36.409000000000006 precision_at_10 9.712 precision_at_100 1.584 precision_at_1000 0.182 precision_at_3 21.096999999999998 precision_at_5 15.498999999999999 recall_at_1 23.746000000000002 recall_at_10 53.596 recall_at_100 85.232 recall_at_1000 98.092 recall_at_3 37.226 recall_at_5 44.187 -
C-MTEB/CovidRetrieval (Dev Split)
Metric Value map_at_1 61.38 map_at_10 71.23 map_at_100 71.61800000000001 map_at_1000 71.63000000000001 map_at_3 69.31 map_at_5 70.403 mrr_at_1 61.538000000000004 mrr_at_10 71.28999999999999 mrr_at_100 71.666 mrr_at_1000 71.678 mrr_at_3 69.44200000000001 mrr_at_5 70.506 ndcg_at_1 61.538000000000004 ndcg_at_10 75.626 ndcg_at_100 77.449 ndcg_at_1000 77.73400000000001 ndcg_at_3 71.75200000000001 ndcg_at_5 73.695 precision_at_1 61.538000000000004 precision_at_10 9.009 precision_at_100 0.9860000000000001 precision_at_1000 0.101 precision_at_3 26.379 precision_at_5 16.797 recall_at_1 61.38 recall_at_10 89.199 recall_at_100 97.576 recall_at_1000 99.789 recall_at_3 78.635 recall_at_5 83.325 -
C-MTEB/DuRetrieval (Dev Split)
Metric Value map_at_1 23.067 map_at_10 70.658 map_at_100 73.85300000000001 map_at_1000 73.925 map_at_3 48.391 map_at_5 61.172000000000004 mrr_at_1 83.1 mrr_at_10 88.214 mrr_at_100 88.298 mrr_at_1000 88.304 mrr_at_3 87.717 mrr_at_5 88.03699999999999 ndcg_at_1 83.1 ndcg_at_10 79.89 ndcg_at_100 83.829 ndcg_at_1000 84.577 ndcg_at_3 78.337 ndcg_at_5 77.224 precision_at_1 83.1 precision_at_10 38.934999999999995 precision_at_100 4.6690000000000005 precision_at_1000 0.484 precision_at_3 70.48299999999999 precision_at_5 59.68 recall_at_1 23.067 recall_at_10 81.702 recall_at_100 94.214 recall_at_1000 98.241 recall_at_3 51.538 recall_at_5 67.39 -
C-MTEB/EcomRetrieval (Dev Split)
Metric Value map_at_1 49.8 map_at_10 59.46399999999999 map_at_100 60.063 map_at_1000 60.08 map_at_3 56.833 map_at_5 58.438 mrr_at_1 49.8 mrr_at_10 59.46399999999999 mrr_at_100 60.063 mrr_at_1000 60.08 mrr_at_3 56.833 mrr_at_5 58.438 ndcg_at_1 49.8 ndcg_at_10 64.48 ndcg_at_100 67.314 ndcg_at_1000 67.745 ndcg_at_3 59.06400000000001 ndcg_at_5 61.973 precision_at_1 49.8 precision_at_10 8.04 precision_at_100 0.935 precision_at_1000 0.097 precision_at_3 21.833 precision_at_5 14.52 recall_at_1 49.8 recall_at_10 80.4 recall_at_100 93.5 recall_at_1000 96.8 recall_at_3 65.5 recall_at_5 72.6 -
C-MTEB/MMarcoRetrieval (Dev Split)
Metric Value map_at_1 57.206999999999994 map_at_10 66.622 map_at_100 67.12700000000001 map_at_1000 67.145 map_at_3 64.587 map_at_5 65.827 mrr_at_1 59.312 mrr_at_10 67.387 mrr_at_100 67.836 mrr_at_1000 67.851 mrr_at_3 65.556 mrr_at_5 66.66 ndcg_at_1 59.312 ndcg_at_10 70.748 ndcg_at_100 73.076 ndcg_at_1000 73.559 ndcg_at_3 66.81200000000001 ndcg_at_5 68.92399999999999 precision_at_1 59.312 precision_at_10 8.798 precision_at_100 0.996 precision_at_1000 0.104 precision_at_3 25.487 precision_at_5 16.401 recall_at_1 57.206999999999994 recall_at_10 82.767 recall_at_100 93.449 recall_at_1000 97.262 recall_at_3 72.271 recall_at_5 77.291 -
C-MTEB/MedicalRetrieval (Dev Split)
Metric Value map_at_1 51.4 map_at_10 57.091 map_at_100 57.652 map_at_1000 57.703 map_at_3 55.733 map_at_5 56.363 mrr_at_1 51.7 mrr_at_10 57.243 mrr_at_100 57.80499999999999 mrr_at_1000 57.855999999999995 mrr_at_3 55.883 mrr_at_5 56.513000000000005 ndcg_at_1 51.4 ndcg_at_10 59.948 ndcg_at_100 63.064 ndcg_at_1000 64.523 ndcg_at_3 57.089999999999996 ndcg_at_5 58.214 precision_at_1 51.4 precision_at_10 6.9 precision_at_100 0.845 precision_at_1000 0.096 precision_at_3 20.333000000000002 precision_at_5 12.740000000000002 recall_at_1 51.4 recall_at_10 69.0 recall_at_100 84.5 recall_at_1000 96.2 recall_at_3 61.0 recall_at_5 63.7
6. Pair Classification
-
C-MTEB/CMNLI (Validation Split)
Metric Value cos_sim_accuracy 82.66987372218881 cos_sim_ap 90.28715189799232 cos_sim_f1 84.108318049412 cos_sim_precision 78.0849358974359 cos_sim_recall 91.13864858545709 dot_accuracy 82.66987372218881 dot_ap 90.29346021403634 dot_f1 84.108318049412 dot_precision 78.0849358974359 dot_recall 91.13864858545709 euclidean_accuracy 82.66987372218881 euclidean_ap 90.28656734732074 euclidean_f1 84.108318049412 euclidean_precision 78.0849358974359 euclidean_recall 91.13864858545709 manhattan_accuracy 82.70595309681299 manhattan_ap 90.25413574022456 manhattan_f1 83.9924670433145 manhattan_precision 79.81052631578947 manhattan_recall 88.63689501987373 max_accuracy 82.70595309681299 max_ap 90.29346021403634 max_f1 84.108318049412 -
C-MTEB/OCNLI (Validation Split)
Metric Value cos_sim_accuracy 81.15863562533838 cos_sim_ap 84.84571607908443 cos_sim_f1 82.55872063968016 cos_sim_precision 78.36812144212524 cos_sim_recall 87.22280887011615 dot_accuracy 81.15863562533838 dot_ap 84.84571607908443 dot_f1 82.55872063968016 dot_precision 78.36812144212524 dot_recall 87.22280887011615 euclidean_accuracy 81.15863562533838 euclidean_ap 84.84571607908443 euclidean_f1 82.55872063968016 euclidean_precision 78.36812144212524 euclidean_recall 87.22280887011615 manhattan_accuracy 80.7796426637791 manhattan_ap 84.81524098914134 manhattan_f1 82.36462990561351 manhattan_precision 77.76735459662288 manhattan_recall 87.53959873284055 max_accuracy 81.15863562533838 max_ap 84.84571607908443 max_f1 82.55872063968016
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