%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)
JA
GIST Embedding V0
G
GIST Embedding V0
avsolatorioによって開発
GIST-Embedding-v0 は sentence-transformers ベースの文埋め込みモデルで、主に文の類似度計算と特徴抽出タスクに使用されます。
ダウンロード数 252.21k
リリース時間 : 4/25/2025
モデル概要
このモデルは文を高次元ベクトル表現に変換でき、文の類似度計算、テキスト分類、情報検索などの様々な自然言語処理タスクに適用可能です。
モデル特徴
高性能文埋め込み
複数のベンチマークテストで優れた性能を発揮し、文の意味を正確に捉えることができます。
多機能アプリケーション
分類、クラスタリング、検索など、様々な自然言語処理タスクをサポートします。
効率的な特徴抽出
文を高速で高次元ベクトルに変換でき、後続の処理や分析が容易です。
モデル能力
文の類似度計算
テキスト分類
情報検索
テキストクラスタリング
特徴抽出
使用事例
電子商取引
商品レビュー分類
Amazon商品レビューの感情分析（ポジティブ/ネガティブ）に使用されます。
精度：93.51%
虚偽レビュー検出
Amazonプラットフォーム上の虚偽レビューを識別します。
精度：75.96%
学術研究
論文クラスタリング
arXivとbiorxivの学術論文をテーマ別にクラスタリングします。
v_measure：42.74-48.29
質問応答システム
重複質問識別
AskUbuntuコミュニティで重複する技術質問を識別します。
mrr：75.46
language:
- en library_name: sentence-transformers license: mit pipeline_tag: sentence-similarity tags:
- feature-extraction
- mteb
- sentence-similarity
- sentence-transformers
model-index:
- name: GIST-Embedding-v0
results:
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (en)
config: en
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
- type: accuracy value: 75.95522388059702
- type: ap value: 38.940434354439276
- type: f1 value: 69.88686275888114
- task:
type: Classification
dataset:
type: mteb/amazon_polarity
name: MTEB AmazonPolarityClassification
config: default
split: test
revision: e2d317d38cd51312af73b3d32a06d1a08b442046
metrics:
- type: accuracy value: 93.51357499999999
- type: ap value: 90.30414241486682
- type: f1 value: 93.50552829047328
- task:
type: Classification
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (en)
config: en
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:
- type: accuracy value: 50.446000000000005
- type: f1 value: 49.76432659699279
- task:
type: Retrieval
dataset:
type: arguana
name: MTEB ArguAna
config: default
split: test
revision: None
metrics:
- type: map_at_1 value: 38.265
- type: map_at_10 value: 54.236
- type: map_at_100 value: 54.81399999999999
- type: map_at_1000 value: 54.81700000000001
- type: map_at_3 value: 49.881
- type: map_at_5 value: 52.431000000000004
- type: mrr_at_1 value: 38.265
- type: mrr_at_10 value: 54.152
- type: mrr_at_100 value: 54.730000000000004
- type: mrr_at_1000 value: 54.733
- type: mrr_at_3 value: 49.644
- type: mrr_at_5 value: 52.32599999999999
- type: ndcg_at_1 value: 38.265
- type: ndcg_at_10 value: 62.62
- type: ndcg_at_100 value: 64.96600000000001
- type: ndcg_at_1000 value: 65.035
- type: ndcg_at_3 value: 53.691
- type: ndcg_at_5 value: 58.303000000000004
- type: precision_at_1 value: 38.265
- type: precision_at_10 value: 8.919
- type: precision_at_100 value: 0.991
- type: precision_at_1000 value: 0.1
- type: precision_at_3 value: 21.573999999999998
- type: precision_at_5 value: 15.192
- type: recall_at_1 value: 38.265
- type: recall_at_10 value: 89.189
- type: recall_at_100 value: 99.14699999999999
- type: recall_at_1000 value: 99.644
- type: recall_at_3 value: 64.723
- type: recall_at_5 value: 75.96000000000001
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-p2p
name: MTEB ArxivClusteringP2P
config: default
split: test
revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d
metrics:
- type: v_measure value: 48.287087887491744
- task:
type: Clustering
dataset:
type: mteb/arxiv-clustering-s2s
name: MTEB ArxivClusteringS2S
config: default
split: test
revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53
metrics:
- type: v_measure value: 42.74244928943812
- task:
type: Reranking
dataset:
type: mteb/askubuntudupquestions-reranking
name: MTEB AskUbuntuDupQuestions
config: default
split: test
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
metrics:
- type: map value: 62.68814324295771
- type: mrr value: 75.46266983247591
- task:
type: STS
dataset:
type: mteb/biosses-sts
name: MTEB BIOSSES
config: default
split: test
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
metrics:
- type: cos_sim_pearson value: 90.45240209600391
- type: cos_sim_spearman value: 87.95079919934645
- type: euclidean_pearson value: 88.93438602492702
- type: euclidean_spearman value: 88.28152962682988
- type: manhattan_pearson value: 88.92193964325268
- type: manhattan_spearman value: 88.21466063329498
- task:
type: BitextMining
dataset:
type: mteb/bucc-bitext-mining
name: MTEB BUCC (de-en)
config: de-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: accuracy value: 15.605427974947808
- type: f1 value: 14.989877233698866
- type: precision value: 14.77906814441261
- type: recall value: 15.605427974947808
- task:
type: BitextMining
dataset:
type: mteb/bucc-bitext-mining
name: MTEB BUCC (fr-en)
config: fr-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: accuracy value: 33.38102575390711
- type: f1 value: 32.41704114719127
- type: precision value: 32.057363829835964
- type: recall value: 33.38102575390711
- task:
type: BitextMining
dataset:
type: mteb/bucc-bitext-mining
name: MTEB BUCC (ru-en)
config: ru-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: accuracy value: 0.1939729823346034
- type: f1 value: 0.17832215223820772
- type: precision value: 0.17639155671715423
- type: recall value: 0.1939729823346034
- task:
type: BitextMining
dataset:
type: mteb/bucc-bitext-mining
name: MTEB BUCC (zh-en)
config: zh-en
split: test
revision: d51519689f32196a32af33b075a01d0e7c51e252
metrics:
- type: accuracy value: 3.0542390731964195
- type: f1 value: 2.762857644374232
- type: precision value: 2.6505178163945935
- type: recall value: 3.0542390731964195
- task:
type: Classification
dataset:
type: mteb/banking77
name: MTEB Banking77Classification
config: default
split: test
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
metrics:
- type: accuracy value: 87.29545454545453
- type: f1 value: 87.26415991342238
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-p2p
name: MTEB BiorxivClusteringP2P
config: default
split: test
revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40
metrics:
- type: v_measure value: 39.035319537839484
- task:
type: Clustering
dataset:
type: mteb/biorxiv-clustering-s2s
name: MTEB BiorxivClusteringS2S
config: default
split: test
revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908
metrics:
- type: v_measure value: 36.667313307057285
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackAndroidRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1 value: 33.979
- type: map_at_10 value: 46.275
- type: map_at_100 value: 47.975
- type: map_at_1000 value: 48.089
- type: map_at_3 value: 42.507
- type: map_at_5 value: 44.504
- type: mrr_at_1 value: 42.346000000000004
- type: mrr_at_10 value: 53.013
- type: mrr_at_100 value: 53.717000000000006
- type: mrr_at_1000 value: 53.749
- type: mrr_at_3 value: 50.405
- type: mrr_at_5 value: 51.915
- type: ndcg_at_1 value: 42.346000000000004
- type: ndcg_at_10 value: 53.179
- type: ndcg_at_100 value: 58.458
- type: ndcg_at_1000 value: 60.057
- type: ndcg_at_3 value: 48.076
- type: ndcg_at_5 value: 50.283
- type: precision_at_1 value: 42.346000000000004
- type: precision_at_10 value: 10.386
- type: precision_at_100 value: 1.635
- type: precision_at_1000 value: 0.20600000000000002
- type: precision_at_3 value: 23.413999999999998
- type: precision_at_5 value: 16.624
- type: recall_at_1 value: 33.979
- type: recall_at_10 value: 65.553
- type: recall_at_100 value: 87.18599999999999
- type: recall_at_1000 value: 97.25200000000001
- type: recall_at_3 value: 50.068999999999996
- type: recall_at_5 value: 56.882
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackEnglishRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1 value: 31.529
- type: map_at_10 value: 42.219
- type: map_at_100 value: 43.408
- type: map_at_1000 value: 43.544
- type: map_at_3 value: 39.178000000000004
- type: map_at_5 value: 40.87
- type: mrr_at_1 value: 39.873
- type: mrr_at_10 value: 48.25
- type: mrr_at_100 value: 48.867
- type: mrr_at_1000 value: 48.908
- type: mrr_at_3 value: 46.03
- type: mrr_at_5 value: 47.355000000000004
- type: ndcg_at_1 value: 39.873
- type: ndcg_at_10 value: 47.933
- type: ndcg_at_100 value: 52.156000000000006
- type: ndcg_at_1000 value: 54.238
- type: ndcg_at_3 value: 43.791999999999994
- type: ndcg_at_5 value: 45.678999999999995
- type: precision_at_1 value: 39.873
- type: precision_at_10 value: 9.032
- type: precision_at_100 value: 1.419
- type: precision_at_1000 value: 0.192
- type: precision_at_3 value: 21.231
- type: precision_at_5 value: 14.981
- type: recall_at_1 value: 31.529
- type: recall_at_10 value: 57.925000000000004
- type: recall_at_100 value: 75.89
- type: recall_at_1000 value: 89.007
- type: recall_at_3 value: 45.363
- type: recall_at_5 value: 50.973
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackGamingRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1 value: 41.289
- type: map_at_10 value: 54.494
- type: map_at_100 value: 55.494
- type: map_at_1000 value: 55.545
- type: map_at_3 value: 51.20099999999999
- type: map_at_5 value: 53.147
- type: mrr_at_1 value: 47.335
- type: mrr_at_10 value: 57.772
- type: mrr_at_100 value: 58.428000000000004
- type: mrr_at_1000 value: 58.453
- type: mrr_at_3 value: 55.434000000000005
- type: mrr_at_5 value: 56.8
- type: ndcg_at_1 value: 47.335
- type: ndcg_at_10 value: 60.382999999999996
- type: ndcg_at_100 value: 64.294
- type: ndcg_at_1000 value: 65.211
- type: ndcg_at_3 value: 55.098
- type: ndcg_at_5 value: 57.776
- type: precision_at_1 value: 47.335
- type: precision_at_10 value: 9.724
- type: precision_at_100 value: 1.26
- type: precision_at_1000 value: 0.13699999999999998
- type: precision_at_3 value: 24.786
- type: precision_at_5 value: 16.977999999999998
- type: recall_at_1 value: 41.289
- type: recall_at_10 value: 74.36399999999999
- type: recall_at_100 value: 91.19800000000001
- type: recall_at_1000 value: 97.508
- type: recall_at_3 value: 60.285
- type: recall_at_5 value: 66.814
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackGisRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1 value: 28.816999999999997
- type: map_at_10 value: 37.856
- type: map_at_100 value: 38.824
- type: map_at_1000 value: 38.902
- type: map_at_3 value: 34.982
- type: map_at_5 value: 36.831
- type: mrr_at_1 value: 31.073
- type: mrr_at_10 value: 39.985
- type: mrr_at_100 value: 40.802
- type: mrr_at_1000 value: 40.861999999999995
- type: mrr_at_3 value: 37.419999999999995
- type: mrr_at_5 value: 39.104
- type: ndcg_at_1 value: 31.073
- type: ndcg_at_10 value: 42.958
- type: ndcg_at_100 value: 47.671
- type: ndcg_at_1000 value: 49.633
- type: ndcg_at_3 value: 37.602000000000004
- type: ndcg_at_5 value: 40.688
- type: precision_at_1 value: 31.073
- type: precision_at_10 value: 6.531000000000001
- type: precision_at_100 value: 0.932
- type: precision_at_1000 value: 0.11399999999999999
- type: precision_at_3 value: 15.857
- type: precision_at_5 value: 11.209
- type: recall_at_1 value: 28.816999999999997
- type: recall_at_10 value: 56.538999999999994
- type: recall_at_100 value: 78.17699999999999
- type: recall_at_1000 value: 92.92200000000001
- type: recall_at_3 value: 42.294
- type: recall_at_5 value: 49.842999999999996
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackMathematicaRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1 value: 18.397
- type: map_at_10 value: 27.256999999999998
- type: map_at_100 value: 28.541
- type: map_at_1000 value: 28.658
- type: map_at_3 value: 24.565
- type: map_at_5 value: 26.211000000000002
- type: mrr_at_1 value: 22.761
- type: mrr_at_10 value: 32.248
- type: mrr_at_100 value: 33.171
- type: mrr_at_1000 value: 33.227000000000004
- type: mrr_at_3 value: 29.498
- type: mrr_at_5 value: 31.246000000000002
- type: ndcg_at_1 value: 22.761
- type: ndcg_at_10 value: 32.879999999999995
- type: ndcg_at_100 value: 38.913
- type: ndcg_at_1000 value: 41.504999999999995
- type: ndcg_at_3 value: 27.988000000000003
- type: ndcg_at_5 value: 30.548
- type: precision_at_1 value: 22.761
- type: precision_at_10 value: 6.045
- type: precision_at_100 value: 1.044
- type: precision_at_1000 value: 0.13999999999999999
- type: precision_at_3 value: 13.433
- type: precision_at_5 value: 9.925
- type: recall_at_1 value: 18.397
- type: recall_at_10 value: 45.14
- type: recall_at_100 value: 71.758
- type: recall_at_1000 value: 89.854
- type: recall_at_3 value: 31.942999999999998
- type: recall_at_5 value: 38.249
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackPhysicsRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1 value: 30.604
- type: map_at_10 value: 42.132
- type: map_at_100 value: 43.419000000000004
- type: map_at_1000 value: 43.527
- type: map_at_3 value: 38.614
- type: map_at_5 value: 40.705000000000005
- type: mrr_at_1 value: 37.824999999999996
- type: mrr_at_10 value: 47.696
- type: mrr_at_100 value: 48.483
- type: mrr_at_1000 value: 48.53
- type: mrr_at_3 value: 45.123999999999995
- type: mrr_at_5 value: 46.635
- type: ndcg_at_1 value: 37.824999999999996
- type: ndcg_at_10 value: 48.421
- type: ndcg_at_100 value: 53.568000000000005
- type: ndcg_at_1000 value: 55.574999999999996
- type: ndcg_at_3 value: 42.89
- type: ndcg_at_5 value: 45.683
- type: precision_at_1 value: 37.824999999999996
- type: precision_at_10 value: 8.758000000000001
- type: precision_at_100 value: 1.319
- type: precision_at_1000 value: 0.168
- type: precision_at_3 value: 20.244
- type: precision_at_5 value: 14.533
- type: recall_at_1 value: 30.604
- type: recall_at_10 value: 61.605
- type: recall_at_100 value: 82.787
- type: recall_at_1000 value: 95.78
- type: recall_at_3 value: 46.303
- type: recall_at_5 value: 53.351000000000006
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackProgrammersRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1 value: 26.262999999999998
- type: map_at_10 value: 36.858999999999995
- type: map_at_100 value: 38.241
- type: map_at_1000 value: 38.346999999999994
- type: map_at_3 value: 33.171
- type: map_at_5 value: 35.371
- type: mrr_at_1 value: 32.42
- type: mrr_at_10 value: 42.361
- type: mrr_at_100 value: 43.219
- type: mrr_at_1000 value: 43.271
- type: mrr_at_3 value: 39.593
- type: mrr_at_5 value: 41.248000000000005
- type: ndcg_at_1 value: 32.42
- type: ndcg_at_10 value: 43.081
- type: ndcg_at_100 value: 48.837
- type: ndcg_at_1000 value: 50.954
- type: ndcg_at_3 value: 37.413000000000004
- type: ndcg_at_5 value: 40.239000000000004
- type: precision_at_1 value: 32.42
- type: precision_at_10 value: 8.071
- type: precision_at_100 value: 1.272
- type: precision_at_1000 value: 0.163
- type: precision_at_3 value: 17.922
- type: precision_at_5 value: 13.311
- type: recall_at_1 value: 26.262999999999998
- type: recall_at_10 value: 56.062999999999995
- type: recall_at_100 value: 80.636
- type: recall_at_1000 value: 94.707
- type: recall_at_3 value: 40.425
- type: recall_at_5 value: 47.663
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1 value: 27.86616666666667
- type: map_at_10 value: 37.584999999999994
- type: map_at_100 value: 38.80291666666667
- type: map_at_1000 value: 38.91358333333333
- type: map_at_3 value: 34.498
- type: map_at_5 value: 36.269999999999996
- type: mrr_at_1 value: 33.07566666666667
- type: mrr_at_10 value: 41.92366666666666
- type: mrr_at_100 value: 42.73516666666667
- type: mrr_at_1000 value: 42.785666666666664
- type: mrr_at_3 value: 39.39075
- type: mrr_at_5 value: 40.89133333333334
- type: ndcg_at_1 value: 33.07566666666667
- type: ndcg_at_10 value: 43.19875
- type: ndcg_at_100 value: 48.32083333333334
- type: ndcg_at_1000 value: 50.418000000000006
- type: ndcg_at_3 value: 38.10308333333333
- type: ndcg_at_5 value: 40.5985
- type: precision_at_1 value: 33.07566666666667
- type: precision_at_10 value: 7.581916666666666
- type: precision_at_100 value: 1.1975
- type: precision_at_1000 value: 0.15699999999999997
- type: precision_at_3 value: 17.49075
- type: precision_at_5 value: 12.5135
- type: recall_at_1 value: 27.86616666666667
- type: recall_at_10 value: 55.449749999999995
- type: recall_at_100 value: 77.92516666666666
- type: recall_at_1000 value: 92.31358333333333
- type: recall_at_3 value: 41.324416666666664
- type: recall_at_5 value: 47.72533333333333
- task:
type: Retrieval
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackStatsRetrieval
config: default
split: test
revision: None
metrics:
- type: map_at_1 value: 26.648
- type: map_at_10 value: 33.155
- type: map_at_100 value: 34.149
- type: map_at_1000 value: 34.239000000000004
- type: map_at_3 value: 30.959999999999997
- type: map_at_5 value: 32.172
- type: mrr_at_1 value: 30.061
- type: mrr_at_10 value: 36.229
- type: mrr_at_100 value: 37.088
- type: mrr_at_1000 value: 37.15
- type: mrr_at_3 value: 34.254
- type: mrr_at_5 value: 35.297
- type: ndcg_at_1 value: 30.061
- type: ndcg_at_10 value: 37.247
- type: ndcg_at_100 value: 42.093
- type: ndcg_at_1000 value: 44.45
- type: ndcg_at_3 value: 33.211
- type: ndcg_at_5 value: 35.083999999999996
- type: precision_at_1 value: 30.061
- type: precision_at_10 value: 5.7059999999999995
- type: precision_at_100 value: 0.8880000000000001
- type: precision_at_1000 value: 0.116
- type: precision_at_3 value: 13.957
- type: precision_at_5 value: 9.663
- type: recall_at_1 value: 26.648
- type: recall_at_10 value: 46.85
- type: recall_at_100 value: 68.87
- type: recall_at_1000 value: 86.508
- type: recall_at_3 value: 35.756
- type: recall_at_5 value: 40.376
- task: type: Retrieval dataset: type: BeIR/cqadupstack name: MTEB CQADup
- task:
type: Classification
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (en)
config: en
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:
Jina Embeddings V3
Jina Embeddings V3 は100以上の言語をサポートする多言語文埋め込みモデルで、文の類似度と特徴抽出タスクに特化しています。
テキスト埋め込み
Transformers 複数言語対応
Transformers 複数言語対応J
jinaai
3.7M
911
Ms Marco MiniLM L6 V2
Apache-2.0
MS Marcoパッセージランキングタスクで訓練されたクロスエンコーダモデル、情報検索におけるクエリ-パッセージ関連性スコアリング用
テキスト埋め込み 英語
M
cross-encoder
2.5M
86
Opensearch Neural Sparse Encoding Doc V2 Distill
Apache-2.0
蒸留技術に基づくスパース検索モデルで、OpenSearch向けに最適化されており、推論不要のドキュメントエンコーディングをサポートし、検索関連性と効率性においてV1版を上回ります
テキスト埋め込み Transformers 英語
Transformers 英語O
opensearch-project
1.8M
7
Sapbert From PubMedBERT Fulltext
Apache-2.0
PubMedBERTに基づく生物医学エンティティ表現モデルで、自己アライメント事前学習により意味関係の捕捉を最適化します。
テキスト埋め込み 英語
S
cambridgeltl
1.7M
49
Gte Large
MIT
GTE-Largeは強力なセンテンストランスフォーマーモデルで、文の類似度とテキスト埋め込みタスクに特化しており、複数のベンチマークテストで優れた性能を発揮します。
テキスト埋め込み 英語
G
thenlper
1.5M
278
Gte Base En V1.5
Apache-2.0
GTE-base-en-v1.5 は英語の文章変換モデルで、文章類似度タスクに特化しており、複数のテキスト埋め込みベンチマークで優れた性能を発揮します。
テキスト埋め込み Transformers 複数言語対応
Transformers 複数言語対応G
Alibaba-NLP
1.5M
63
Gte Multilingual Base
Apache-2.0
GTE Multilingual Base は50以上の言語をサポートする多言語文埋め込みモデルで、文類似度計算などのタスクに適しています。
テキスト埋め込み Transformers 複数言語対応
Transformers 複数言語対応G
Alibaba-NLP
1.2M
246
Polybert
polyBERTは、完全に機械駆動の超高速ポリマー情報学を実現するための化学言語モデルです。PSMILES文字列を600次元の密なフィンガープリントにマッピングし、ポリマー化学構造を数値形式で表現します。
テキスト埋め込み Transformers
TransformersP
kuelumbus
1.0M
5
Bert Base Turkish Cased Mean Nli Stsb Tr
Apache-2.0
トルコ語BERTベースの文埋め込みモデルで、意味的類似性タスクに最適化
テキスト埋め込み Transformers その他
Transformers その他B
emrecan
1.0M
40
GIST Small Embedding V0
MIT
BAAI/bge-small-en-v1.5モデルを微調整したテキスト埋め込みモデルで、MEDIデータセットとMTEB分類タスクデータセットで訓練され、検索タスクのクエリエンコーディング能力を最適化しました。
テキスト埋め込み
Safetensors 英語
Safetensors 英語G
avsolatorio
945.68k
29
おすすめAIモデル
Llama 3 Typhoon V1.5x 8b Instruct
タイ語専用に設計された80億パラメータの命令モデルで、GPT-3.5-turboに匹敵する性能を持ち、アプリケーションシナリオ、検索拡張生成、制限付き生成、推論タスクを最適化
大規模言語モデル Transformers 複数言語対応
Transformers 複数言語対応L
scb10x
3,269
16
Cadet Tiny
Openrail
Cadet-TinyはSODAデータセットでトレーニングされた超小型対話モデルで、エッジデバイス推論向けに設計されており、体積はCosmo-3Bモデルの約2％です。
対話システム Transformers 英語
Transformers 英語C
ToddGoldfarb
2,691
6
Roberta Base Chinese Extractive Qa
RoBERTaアーキテクチャに基づく中国語抽出型QAモデルで、与えられたテキストから回答を抽出するタスクに適しています。
質問応答システム 中国語
R
uer
2,694
98