GIST-Embedding-v0 Open-Source Sentence Embedding Model - Free for Sentence Similarity Calculation and Feature Extraction

GIST Embedding V0

Developed by avsolatorio

GIST-Embedding-v0 is a sentence embedding model based on sentence-transformers, mainly used for sentence similarity calculation and feature extraction tasks.

Text Embedding

Safetensors

EnglishOpen Source License:MIT #Sentence similarity calculation #Multi-task evaluation #High-precision feature extraction

Downloads 252.21k

Release Time : 4/25/2025

Model Overview

This model can convert sentences into high-dimensional vector representations and is suitable for various natural language processing tasks, such as sentence similarity calculation, text classification, and information retrieval.

Model Features

High-performance sentence embedding

Performs excellently in multiple benchmark tests and can accurately capture sentence semantics.

Multi-functional application

Supports multiple natural language processing tasks, including classification, clustering, retrieval, etc.

Efficient feature extraction

Can quickly convert sentences into high-dimensional vectors for subsequent processing and analysis.

Model Capabilities

Sentence similarity calculation

Text classification

Information retrieval

Text clustering

Feature extraction

Use Cases

E-commerce

Product review classification

Used for sentiment analysis (positive/negative) of Amazon product reviews.

Accuracy: 93.51%

Counterfactual review detection

Identify counterfactual reviews on the Amazon platform.

Accuracy: 75.96%

Academic research

Paper clustering

Perform topic clustering on academic papers from arXiv and biorxiv.

v_measure: 42.74 - 48.29

Question answering system

Duplicate question identification

Identify duplicate technical questions in the AskUbuntu community.

mrr: 75.46

🚀 GIST-Embedding-v0

This is a model based on the sentence-transformers library, focusing on sentence similarity tasks. It has been tested on multiple datasets in the MTEB benchmark, demonstrating its performance in various natural language processing tasks such as classification, retrieval, clustering, reranking, and semantic text similarity.

📚 Documentation

Model Information

Property	Details
Library Name	sentence-transformers
Pipeline Tag	sentence-similarity
Tags	feature-extraction, mteb, sentence-similarity, sentence-transformers
Model Name	GIST-Embedding-v0
License	MIT

Performance Metrics

The model has been evaluated on multiple tasks and datasets, and the following are the detailed performance metrics:

Classification Tasks

Dataset	Accuracy	AP	F1
MTEB AmazonCounterfactualClassification (en)	75.95522388059702	38.940434354439276	69.88686275888114
MTEB AmazonPolarityClassification	93.51357499999999	90.30414241486682	93.50552829047328
MTEB AmazonReviewsClassification (en)	50.446000000000005	-	49.76432659699279
MTEB Banking77Classification	87.29545454545453	-	87.26415991342238

Retrieval Tasks

Dataset	MAP@1	MAP@10	MAP@100	MAP@1000	MRR@1	MRR@10	MRR@100	MRR@1000	NDCG@1	NDCG@10	NDCG@100	NDCG@1000	Precision@1	Precision@10	Precision@100	Precision@1000	Recall@1	Recall@10	Recall@100	Recall@1000
MTEB ArguAna	38.265	54.236	54.81399999999999	54.81700000000001	38.265	54.152	54.730000000000004	54.733	38.265	62.62	64.96600000000001	65.035	38.265	8.919	0.991	0.1	38.265	89.189	99.14699999999999	99.644
MTEB CQADupstackAndroidRetrieval	33.979	46.275	47.975	48.089	42.346000000000004	53.013	53.717000000000006	53.749	42.346000000000004	53.179	58.458	60.057	42.346000000000004	10.386	1.635	0.20600000000000002	33.979	65.553	87.18599999999999	97.25200000000001
MTEB CQADupstackEnglishRetrieval	31.529	42.219	43.408	43.544	39.873	48.25	48.867	48.908	39.873	47.933	52.156000000000006	54.238	39.873	9.032	1.419	0.192	31.529	57.925000000000004	75.89	89.007
MTEB CQADupstackGamingRetrieval	41.289	54.494	55.494	55.545	47.335	57.772	58.428000000000004	58.453	47.335	60.382999999999996	64.294	65.211	47.335	9.724	1.26	0.13699999999999998	41.289	74.36399999999999	91.19800000000001	97.508
MTEB CQADupstackGisRetrieval	28.816999999999997	37.856	38.824	38.902	31.073	39.985	40.802	40.861999999999995	31.073	42.958	47.671	49.633	31.073	6.531000000000001	0.932	0.11399999999999999	28.816999999999997	56.538999999999994	78.17699999999999	92.92200000000001
MTEB CQADupstackMathematicaRetrieval	18.397	27.256999999999998	28.541	28.658	22.761	32.248	33.171	33.227000000000004	22.761	32.879999999999995	38.913	41.504999999999995	22.761	6.045	1.044	0.13999999999999999	18.397	45.14	71.758	89.854
MTEB CQADupstackPhysicsRetrieval	30.604	42.132	43.419000000000004	43.527	37.824999999999996	47.696	48.483	48.53	37.824999999999996	48.421	53.568000000000005	55.574999999999996	37.824999999999996	8.758000000000001	1.319	0.168	30.604	61.605	82.787	95.78
MTEB CQADupstackProgrammersRetrieval	26.262999999999998	36.858999999999995	38.241	38.346999999999994	32.42	42.361	43.219	43.271	32.42	43.081	48.837	50.954	32.42	8.071	1.272	0.163	26.262999999999998	56.062999999999995	80.636	94.707
MTEB CQADupstackRetrieval	27.86616666666667	37.584999999999994	38.80291666666667	38.91358333333333	33.07566666666667	41.92366666666666	42.73516666666667	42.785666666666664	33.07566666666667	43.19875	48.32083333333334	50.418000000000006	33.07566666666667	7.581916666666666	1.1975	0.15699999999999997	27.86616666666667	55.449749999999995	77.92516666666666	92.31358333333333

Clustering Tasks

Dataset	V-Measure
MTEB ArxivClusteringP2P	48.287087887491744
MTEB ArxivClusteringS2S	42.74244928943812
MTEB BiorxivClusteringP2P	39.035319537839484
MTEB BiorxivClusteringS2S	36.667313307057285

Reranking Tasks

Dataset	MAP	MRR
MTEB AskUbuntuDupQuestions	62.68814324295771	75.46266983247591

STS Tasks

Dataset	Cosine Similarity Pearson	Cosine Similarity Spearman	Euclidean Pearson	Euclidean Spearman	Manhattan Pearson	Manhattan Spearman
MTEB BIOSSES	90.45240209600391	87.95079919934645	88.93438602492702	88.28152962682988	88.92193964325268	88.21466063329498

Bitext Mining Tasks

Dataset	Accuracy	F1	Precision	Recall
MTEB BUCC (de-en)	15.605427974947808	14.989877233698866	14.77906814441261	15.605427974947808
MTEB BUCC (fr-en)	33.38102575390711	32.41704114719127	32.057363829835964	33.38102575390711
MTEB BUCC (ru-en)	0.1939729823346034	0.17832215223820772	0.17639155671715423	0.1939729823346034
MTEB BUCC (zh-en)	3.0542390731964195	2.762857644374232	2.6505178163945935	3.0542390731964195

📄 License

This project is licensed under the MIT License.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご