I
Instructor Xl
由 retrainai 开发
一个基于T5架构的句子嵌入模型，专注于英语文本的语义相似度和信息检索任务。
下载量 22
发布时间 : 12/28/2023
模型介绍
内容详情
替代品
模型简介
该模型是一个基于T5架构的句子嵌入模型，主要用于计算句子相似度、信息检索、文本分类和聚类等自然语言处理任务。它在多个标准数据集上表现出色，特别是在语义相似度和检索任务中。
模型特点
多任务性能
在句子相似度、信息检索、文本分类和聚类等多种任务上表现优异
强大的语义理解
基于T5架构，能够深入理解文本语义，生成高质量的句子嵌入
广泛评估
在MTEB等多个标准数据集上进行了全面评估，验证了其有效性
模型能力
句子相似度计算
信息检索
文本分类
文本聚类
特征提取
文本重排序
提示检索
使用案例
信息检索
问答系统
用于检索与用户问题最相关的答案
在CQADupstack数据集上map@100达到38.79
文档检索
从大量文档中检索相关内容
在ArguAna数据集上ndcg@100达到58.88
文本分类
情感分析
对文本进行正面/负面情感分类
在AmazonPolarity数据集上准确率达到86.54%
意图识别
识别用户查询的意图类别
在Banking77数据集上准确率达到82.66%
语义相似度
重复问题检测
识别语义相似的问题
在AskUbuntuDupQuestions数据集上map达到65.35
语义搜索
基于语义而非关键词匹配的搜索
在BIOSSES数据集上余弦相似度斯皮尔曼相关达到84.15
pipeline_tag: 句子相似度
tags:
- 文本嵌入
- 嵌入向量
- 信息检索
- beir
- 文本分类
- 语言模型
- 文本聚类
- 文本语义相似度
- 文本评估
- 提示检索
- 文本重排序
- sentence-transformers
- 特征提取
- 句子相似度
- transformers
- t5
- 英语
- 句子相似度
- natural_questions
- ms_marco
- fever
- hotpot_qa
- mteb
language: en
inference: false
license: apache-2.0
model-index: - name: final_xl_results
results:- task:
type: 分类
dataset:
type: mteb/amazon_counterfactual
name: MTEB AmazonCounterfactualClassification (en)
config: en
split: test
revision: e8379541af4e31359cca9fbcf4b00f2671dba205
metrics:- type: 准确率
value: 85.08955223880596 - type: 平均精度
value: 52.66066378722476 - type: f1分数
value: 79.63340218960269
- type: 准确率
- task:
type: 分类
dataset:
type: mteb/amazon_polarity
name: MTEB AmazonPolarityClassification
config: default
split: test
revision: e2d317d38cd51312af73b3d32a06d1a08b442046
metrics:- type: 准确率
value: 86.542 - type: 平均精度
value: 81.92695193008987 - type: f1分数
value: 86.51466132573681
- type: 准确率
- task:
type: 分类
dataset:
type: mteb/amazon_reviews_multi
name: MTEB AmazonReviewsClassification (en)
config: en
split: test
revision: 1399c76144fd37290681b995c656ef9b2e06e26d
metrics:- type: 准确率
value: 42.964 - type: f1分数
value: 41.43146249774862
- type: 准确率
- task:
type: 检索
dataset:
type: arguana
name: MTEB ArguAna
config: default
split: test
revision: None
metrics:- type: map@1
value: 29.872 - type: map@10
value: 46.342 - type: map@100
value: 47.152 - type: map@1000
value: 47.154 - type: map@3
value: 41.216 - type: map@5
value: 44.035999999999994 - type: mrr@1
value: 30.939 - type: mrr@10
value: 46.756 - type: mrr@100
value: 47.573 - type: mrr@1000
value: 47.575 - type: mrr@3
value: 41.548 - type: mrr@5
value: 44.425 - type: ndcg@1
value: 29.872 - type: ndcg@10
value: 55.65 - type: ndcg@100
value: 58.88099999999999 - type: ndcg@1000
value: 58.951 - type: ndcg@3
value: 45.0 - type: ndcg@5
value: 50.09 - type: precision@1
value: 29.872 - type: precision@10
value: 8.549 - type: precision@100
value: 0.991 - type: precision@1000
value: 0.1 - type: precision@3
value: 18.658 - type: precision@5
value: 13.669999999999998 - type: recall@1
value: 29.872 - type: recall@10
value: 85.491 - type: recall@100
value: 99.075 - type: recall@1000
value: 99.644 - type: recall@3
value: 55.974000000000004 - type: recall@5
value: 68.35
- type: map@1
- task:
type: 聚类
dataset:
type: mteb/arxiv-clustering-p2p
name: MTEB ArxivClusteringP2P
config: default
split: test
revision: a122ad7f3f0291bf49cc6f4d32aa80929df69d5d
metrics:- type: v_measure
value: 42.452729850641276
- type: v_measure
- task:
type: 聚类
dataset:
type: mteb/arxiv-clustering-s2s
name: MTEB ArxivClusteringS2S
config: default
split: test
revision: f910caf1a6075f7329cdf8c1a6135696f37dbd53
metrics:- type: v_measure
value: 32.21141846480423
- type: v_measure
- task:
type: 重排序
dataset:
type: mteb/askubuntudupquestions-reranking
name: MTEB AskUbuntuDupQuestions
config: default
split: test
revision: 2000358ca161889fa9c082cb41daa8dcfb161a54
metrics:- type: map
value: 65.34710928952622 - type: mrr
value: 77.61124301983028
- type: map
- task:
type: STS
dataset:
type: mteb/biosses-sts
name: MTEB BIOSSES
config: default
split: test
revision: d3fb88f8f02e40887cd149695127462bbcf29b4a
metrics:- type: 余弦相似度斯皮尔曼
value: 84.15312230525639
- type: 余弦相似度斯皮尔曼
- task:
type: 分类
dataset:
type: mteb/banking77
name: MTEB Banking77Classification
config: default
split: test
revision: 0fd18e25b25c072e09e0d92ab615fda904d66300
metrics:- type: 准确率
value: 82.66233766233766 - type: f1分数
value: 82.04175284777669
- type: 准确率
- task:
type: 聚类
dataset:
type: mteb/biorxiv-clustering-p2p
name: MTEB BiorxivClusteringP2P
config: default
split: test
revision: 65b79d1d13f80053f67aca9498d9402c2d9f1f40
metrics:- type: v_measure
value: 37.36697339826455
- type: v_measure
- task:
type: 聚类
dataset:
type: mteb/biorxiv-clustering-s2s
name: MTEB BiorxivClusteringS2S
config: default
split: test
revision: 258694dd0231531bc1fd9de6ceb52a0853c6d908
metrics:- type: v_measure
value: 30.551241447593092
- type: v_measure
- task:
type: 检索
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackAndroidRetrieval
config: default
split: test
revision: None
metrics:- type: map@1
value: 36.797000000000004 - type: map@10
value: 48.46 - type: map@100
value: 49.968 - type: map@1000
value: 50.080000000000005 - type: map@3
value: 44.71 - type: map@5
value: 46.592 - type: mrr@1
value: 45.494 - type: mrr@10
value: 54.747 - type: mrr@100
value: 55.43599999999999 - type: mrr@1000
value: 55.464999999999996 - type: mrr@3
value: 52.361000000000004 - type: mrr@5
value: 53.727000000000004 - type: ndcg@1
value: 45.494 - type: ndcg@10
value: 54.989 - type: ndcg@100
value: 60.096000000000004 - type: ndcg@1000
value: 61.58 - type: ndcg@3
value: 49.977 - type: ndcg@5
value: 51.964999999999996 - type: precision@1
value: 45.494 - type: precision@10
value: 10.558 - type: precision@100
value: 1.6049999999999998 - type: precision@1000
value: 0.203 - type: precision@3
value: 23.796 - type: precision@5
value: 16.881 - type: recall@1
value: 36.797000000000004 - type: recall@10
value: 66.83 - type: recall@100
value: 88.34100000000001 - type: recall@1000
value: 97.202 - type: recall@3
value: 51.961999999999996 - type: recall@5
value: 57.940000000000005
- type: map@1
- task:
type: 检索
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackEnglishRetrieval
config: default
split: test
revision: None
metrics:- type: map@1
value: 32.597 - type: map@10
value: 43.424 - type: map@100
value: 44.78 - type: map@1000
value: 44.913 - type: map@3
value: 40.315 - type: map@5
value: 41.987 - type: mrr@1
value: 40.382 - type: mrr@10
value: 49.219 - type: mrr@100
value: 49.895 - type: mrr@1000
value: 49.936 - type: mrr@3
value: 46.996 - type: mrr@5
value: 48.231 - type: ndcg@1
value: 40.382 - type: ndcg@10
value: 49.318 - type: ndcg@100
value: 53.839999999999996 - type: ndcg@1000
value: 55.82899999999999 - type: ndcg@3
value: 44.914 - type: ndcg@5
value: 46.798 - type: precision@1
value: 40.382 - type: precision@10
value: 9.274000000000001 - type: precision@100
value: 1.497 - type: precision@1000
value: 0.198 - type: precision@3
value: 21.592 - type: precision@5
value: 15.159 - type: recall@1
value: 32.597 - type: recall@10
value: 59.882000000000005 - type: recall@100
value: 78.446 - type: recall@1000
value: 90.88000000000001 - type: recall@3
value: 46.9 - type: recall@5
value: 52.222
- type: map@1
- task:
type: 检索
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackGamingRetrieval
config: default
split: test
revision: None
metrics:- type: map@1
value: 43.8 - type: map@10
value: 57.293000000000006 - type: map@100
value: 58.321 - type: map@1000
value: 58.361 - type: map@3
value: 53.839999999999996 - type: map@5
value: 55.838 - type: mrr@1
value: 49.592000000000006 - type: mrr@10
value: 60.643 - type: mrr@100
value: 61.23499999999999 - type: mrr@1000
value: 61.251999999999995 - type: mrr@3
value: 58.265 - type: mrr@5
value: 59.717 - type: ndcg@1
value: 49.592000000000006 - type: ndcg@10
value: 63.364 - type: ndcg@100
value: 67.167 - type: ndcg@1000
value: 67.867 - type: ndcg@3
value: 57.912 - type: ndcg@5
value: 60.697 - type: precision@1
value: 49.592000000000006 - type: precision@10
value: 10.088 - type: precision@100
value: 1.2930000000000001 - type: precision@1000
value: 0.13899999999999998 - type: precision@3
value: 25.789 - type: precision@5
value: 17.541999999999998 - type: recall@1
value: 43.8 - type: recall@10
value: 77.635 - type: recall@100
value: 93.748 - type: recall@1000
value: 98.468 - type: recall@3
value: 63.223 - type: recall@5
value: 70.122
- type: map@1
- task:
type: 检索
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackGisRetrieval
config: default
split: test
revision: None
metrics:- type: map@1
value: 27.721 - type: map@10
value: 35.626999999999995 - type: map@100
value: 36.719 - type: map@1000
value: 36.8 - type: map@3
value: 32.781 - type: map@5
value: 34.333999999999996 - type: mrr@1
value: 29.604999999999997 - type: mrr@10
value: 37.564 - type: mrr@100
value: 38.505 - type: mrr@1000
value: 38.565 - type: mrr@3
value: 34.727000000000004 - type: mrr@5
value: 36.207 - type: ndcg@1
value: 29.604999999999997 - type: ndcg@10
value: 40.575 - type: ndcg@100
value: 45.613 - type: ndcg@1000
value: 47.676 - type: ndcg@3
value: 34.811 - type: ndcg@5
value: 37.491 - type: precision@1
value: 29.604999999999997 - type: precision@10
value: 6.1690000000000005 - type: precision@100
value: 0.906 - type: precision@1000
value: 0.11199999999999999 - type: precision@3
value: 14.237 - type: precision@5
value: 10.056 - type: recall@1
value: 27.721 - type: recall@10
value: 54.041 - type: recall@100
value: 76.62299999999999 - type: recall@1000
value: 92.134 - type: recall@3
value: 38.582 - type: recall@5
value: 44.989000000000004
- type: map@1
- task:
type: 检索
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackMathematicaRetrieval
config: default
split: test
revision: None
metrics:- type: map@1
value: 16.553 - type: map@10
value: 25.384 - type: map@100
value: 26.655 - type: map@1000
value: 26.778000000000002 - type: map@3
value: 22.733 - type: map@5
value: 24.119 - type: mrr@1
value: 20.149 - type: mrr@10
value: 29.705 - type: mrr@100
value: 30.672 - type: mrr@1000
value: 30.737 - type: mrr@3
value: 27.032 - type: mrr@5
value: 28.369 - type: ndcg@1
value: 20.149 - type: ndcg@10
value: 30.843999999999998 - type: ndcg@100
value: 36.716 - type: ndcg@1000
value: 39.495000000000005 - type: ndcg@3
value: 25.918999999999997 - type: ndcg@5
value: 27.992 - type: precision@1
value: 20.149 - type: precision@10
value: 5.858 - type: precision@100
value: 1.009 - type: precision@1000
value: 0.13799999999999998 - type: precision@3
value: 12.645000000000001 - type: precision@5
value: 9.179 - type: recall@1
value: 16.553 - type: recall@10
value: 43.136 - type: recall@100
value: 68.562 - type: recall@1000
value: 88.208 - type: recall@3
value: 29.493000000000002 - type: recall@5
value: 34.751
- type: map@1
- task:
type: 检索
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackPhysicsRetrieval
config: default
split: test
revision: None
metrics:- type: map@1
value: 28.000999999999998 - type: map@10
value: 39.004 - type: map@100
value: 40.461999999999996 - type: map@1000
value: 40.566 - type: map@3
value: 35.805 - type: map@5
value: 37.672 - type: mrr@1
value: 33.782000000000004 - type: mrr@10
value: 44.702 - type: mrr@100
value: 45.528 - type: mrr@1000
value: 45.576 - type: mrr@3
value: 42.14 - type: mrr@5
value: 43.651 - type: ndcg@1
value: 33.782000000000004 - type: ndcg@10
value: 45.275999999999996 - type: ndcg@100
value: 50.888 - type: ndcg@1000
value: 52.879 - type: ndcg@3
value: 40.191 - type: ndcg@5
value: 42.731 - type: precision@1
value: 33.782000000000004 - type: precision@10
value: 8.200000000000001 - type: precision@100
value: 1.287 - type: precision@1000
value: 0.16199999999999998 - type: precision@3
value: 19.185 - type: precision@5
value: 13.667000000000002 - type: recall@1
value: 28.000999999999998 - type: recall@10
value: 58.131 - type: recall@100
value: 80.869 - type: recall@1000
value: 93.931 - type: recall@3
value: 44.161 - type: recall@5
value: 50.592000000000006
- type: map@1
- task:
type: 检索
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackProgrammersRetrieval
config: default
split: test
revision: None
metrics:- type: map@1
value: 28.047 - type: map@10
value: 38.596000000000004 - type: map@100
value: 40.116 - type: map@1000
value: 40.232 - type: map@3
value: 35.205 - type: map@5
value: 37.076 - type: mrr@1
value: 34.932 - type: mrr@10
value: 44.496 - type: mrr@100
value: 45.47 - type: mrr@1000
value: 45.519999999999996 - type: mrr@3
value: 41.743 - type: mrr@5
value: 43.352000000000004 - type: ndcg@1
value: 34.932 - type: ndcg@10
value: 44.901 - type: ndcg@100
value: 50.788999999999994 - type: ndcg@1000
value: 52.867 - type: ndcg@3
value: 39.449 - type: ndcg@5
value: 41.929 - type: precision@1
value: 34.932 - type: precision@10
value: 8.311 - type: precision@100
value: 1.3050000000000002 - type: precision@1000
value: 0.166 - type: precision@3
value: 18.836 - type: precision@5
value: 13.447000000000001 - type: recall@1
value: 28.047 - type: recall@10
value: 57.717 - type: recall@100
value: 82.182 - type: recall@1000
value: 95.82000000000001 - type: recall@3
value: 42.448 - type: recall@5
value: 49.071
- type: map@1
- task:
type: 检索
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackRetrieval
config: default
split: test
revision: None
metrics:- type: map@1
value: 27.861250000000005 - type: map@10
value: 37.529583333333335 - type: map@100
value: 38.7915 - type: map@1000
value: 38.90558333333335 - type: map@3
value: 34.57333333333333 - type: map@5
value: 36.187166666666656 - type: mrr@1
value: 32.88291666666666 - type: mrr@10
value: 41.79750000000001 - type: mrr@100
value: 42.63183333333333 - type: mrr@1000
value: 42.68483333333333 - type: mrr@3
value: 39.313750000000006 - type: mrr@5
value: 40.70483333333333 - type: ndcg@1
value: 32.88291666666666 - type: ndcg@10
value: 43.09408333333333 - type: ndcg@100
value: 48.22158333333333 - type: ndcg@1000
value: 50.358000000000004 - type: ndcg@3
value: 38.129583333333336 - type: ndcg@5
value: 40.39266666666666 - type: precision@1
value: 32.88291666666666 - type: precision@10
value: 7.5584999999999996 - type: precision@100
value: 1.1903333333333332 - type: precision@1000
value: 0.15658333333333332 - type: precision@3
value: 17.495916666666666 - type: precision@5
value: 12.373833333333332 - type: recall@1
value: 27.861250000000005 - type: recall@10
value: 55.215916666666665 - type: recall@100
value: 77.392 - type: recall@1000
value: 92.04908333333334 - type: recall@3
value: 41.37475 - type: recall@5
value: 47.22908333333333
- type: map@1
- task:
type: 检索
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackStatsRetrieval
config: default
split: test
revision: None
metrics:- type: map@1
value: 25.064999999999998 - type: map@10
value: 31.635999999999996 - type: map@100
value: 32.596000000000004 - type: map@1000
value: 32.695 - type: map@3
value: 29.612 - type: map@5
value: 30.768 - type: mrr@1
value: 28.528 - type: mrr@10
value: 34.717 - type: mrr@100
value: 35.558 - type: mrr@1000
value: 35.626000000000005 - type: mrr@3
value: 32.745000000000005 - type: mrr@5
value: 33.819 - type: ndcg@1
value: 28.528 - type: ndcg@10
value: 35.647 - type: ndcg@100
value: 40.207 - type: ndcg@1000
value: 42.695 - type: ndcg@3
value: 31.878 - type: ndcg@5
value: 33.634 - type: precision@1
value: 28.528 - type: precision@10
value: 5.46 - type: precision@100
value: 0.84 - type: precision@1000
value: 0.11399999999999999 - type: precision@3
value: 13.547999999999998 - type: precision@5
value: 9.325 - type: recall@1
value: 25.064999999999998 - type: recall@10
value: 45.096000000000004 - type: recall@100
value: 65.658 - type: recall@1000
value: 84.128 - type: recall@3
value: 34.337 - type: recall@5
value: 38.849000000000004
- type: map@1
- task:
type: 检索
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackTexRetrieval
config: default
split: test
revision: None
metrics:- type: map@1
value: 17.276 - type: map@10
value: 24.535 - type: map@100
value: 25.655 - type: map@1000
value: 25.782 - type: map@3
value: 22.228 - type: map@5
value: 23.612 - type: mrr@1
value: 21.266 - type: mrr@10
value: 28.474 - type: mrr@100
value: 29.398000000000003 - type: mrr@1000
value: 29.482000000000003 - type: mrr@3
value: 26.245 - type: mrr@5
value: 27.624 - type: ndcg@1
value: 21.266 - type: ndcg@10
value: 29.087000000000003 - type: ndcg@100
value: 34.374 - type: ndcg@1000
value: 37.433 - type: ndcg@3
value: 25.040000000000003 - type: ndcg@5
value: 27.116 - type: precision@1
value: 21.266 - type: precision@10
value: 5.258 - type: precision@100
value: 0.9299999999999999 - type: precision@1000
value: 0.13699999999999998 - type: precision@3
value: 11.849 - type: precision@5
value: 8.699 - type: recall@1
value: 17.276 - type: recall@10
value: 38.928000000000004 - type: recall@100
value: 62.529 - type: recall@1000
value: 84.44800000000001 - type: recall@3
value: 27.554000000000002 - type: recall@5
value: 32.915
- type: map@1
- task:
type: 检索
dataset:
type: BeIR/cqadupstack
name: MTEB CQADupstackUnixRetrieval
config: default
split: test
revision: None
metrics:- type: map@1
value: 27.297 - type: map@10
value: 36.957 - type: map@100
value: 38.252 - type: map@1000
value: 38.356 - type: map@3
value: 34.121 - type: map@5
value: 35.782000000000004 - type: mrr@1
value: 32.275999999999996 - type: mrr@10
value: 41.198 - type: mrr@100
value: 42.131 - type: mrr@1000
value: 42.186 - type: mrr@3
value: 38.557 - type: mrr@5
value: 40.12 - type: ndcg@1
value: 32.275999
- type: map@1
- task:
Jina Embeddings V3
Jina Embeddings V3 是一个多语言句子嵌入模型，支持超过100种语言，专注于句子相似度和特征提取任务。
文本嵌入
Transformers
Transformers 支持多种语言
J
jinaai
3.7M
911
Ms Marco MiniLM L6 V2
Apache-2.0
基于MS Marco段落排序任务训练的交叉编码器模型，用于信息检索中的查询-段落相关性评分
文本嵌入
英语
M
cross-encoder
2.5M
86
Opensearch Neural Sparse Encoding Doc V2 Distill
Apache-2.0
基于蒸馏技术的稀疏检索模型，专为OpenSearch优化，支持免推理文档编码，在搜索相关性和效率上优于V1版本
文本嵌入 Transformers
Transformers 英语
O
opensearch-project
1.8M
7
Sapbert From PubMedBERT Fulltext
Apache-2.0
基于PubMedBERT的生物医学实体表征模型，通过自对齐预训练优化语义关系捕捉
文本嵌入
英语
S
cambridgeltl
1.7M
49
Gte Large
MIT
GTE-Large 是一个强大的句子转换器模型，专注于句子相似度和文本嵌入任务，在多个基准测试中表现出色。
文本嵌入
英语
G
thenlper
1.5M
278
Gte Base En V1.5
Apache-2.0
GTE-base-en-v1.5 是一个英文句子转换器模型，专注于句子相似度任务，在多个文本嵌入基准测试中表现优异。
文本嵌入 Transformers
Transformers 支持多种语言
G
Alibaba-NLP
1.5M
63
Gte Multilingual Base
Apache-2.0
GTE Multilingual Base 是一个多语言的句子嵌入模型，支持超过50种语言，适用于句子相似度计算等任务。
文本嵌入 Transformers
Transformers 支持多种语言
G
Alibaba-NLP
1.2M
246
Polybert
polyBERT是一个化学语言模型，旨在实现完全由机器驱动的超快聚合物信息学。
文本嵌入 Transformers
TransformersP
kuelumbus
1.0M
5
Bert Base Turkish Cased Mean Nli Stsb Tr
Apache-2.0
基于土耳其语BERT的句子嵌入模型，专为语义相似度任务优化
文本嵌入 Transformers
Transformers 其他
B
emrecan
1.0M
40
GIST Small Embedding V0
MIT
基于BAAI/bge-small-en-v1.5模型微调的文本嵌入模型，通过MEDI数据集与MTEB分类任务数据集训练，优化了检索任务的查询编码能力。
文本嵌入
Safetensors
Safetensors 英语
G
avsolatorio
945.68k
29
精选推荐AI模型
Llama 3 Typhoon V1.5x 8b Instruct
专为泰语设计的80亿参数指令模型，性能媲美GPT-3.5-turbo，优化了应用场景、检索增强生成、受限生成和推理任务
大型语言模型 Transformers
Transformers 支持多种语言
L
scb10x
3,269
16
Cadet Tiny
Openrail
Cadet-Tiny是一个基于SODA数据集训练的超小型对话模型，专为边缘设备推理设计，体积仅为Cosmo-3B模型的2%左右。
对话系统 Transformers
Transformers 英语
C
ToddGoldfarb
2,691
6
Roberta Base Chinese Extractive Qa
基于RoBERTa架构的中文抽取式问答模型，适用于从给定文本中提取答案的任务。
问答系统
中文
R
uer
2,694
98
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20none;%20}%20.st1%20{%20fill:%20%235ce6cf;%20}%20.st2%20{%20fill:%20%230080ff;%20}%20.st3%20{%20clip-path:%20url(%23clippath);%20}%20%3c/style%3e%3cclipPath%20id='clippath'%3e%3crect%20class='st0'%20y='0'%20width='120'%20height='32'/%3e%3c/clipPath%3e%3c/defs%3e%3cg%20class='st3'%3e%3cg%3e%3cpath%20class='st1'%20d='M22.4,32H3.2c-1,0-2-.5-2.6-1.4-.6-.9-.7-2-.4-2.9L9.8,2.1C10.3.8,11.5,0,12.8,0s2.5.8,3,2.1l9.6,25.6c.4,1,.2,2.1-.4,2.9-.6.9-1.6,1.4-2.6,1.4ZM7.8,25.6h10l-5-13.3-5,13.3Z'/%3e%3cpath%20class='st2'%20d='M33.6,32c-1.3,0-2.5-.8-3-2.1L21,4.3c-.6-1.7.2-3.5,1.9-4.1,1.7-.6,3.5.2,4.1,1.9l9.6,25.6c.6,1.7-.2,3.5-1.9,4.1-.4.1-.8.2-1.1.2h0Z'/%3e%3cpath%20d='M71.8,9.1h-6.9v4.6h6.9c2.5,0,4.6,2,4.6,4.6h-6.9c-3.8,0-6.9,3.1-6.9,6.9s3.1,6.9,6.9,6.9h2.3c1.7,0,3.2-.4,4.6-1.2v1.2h4.6v-13.7c0-5-4.1-9.1-9.1-9.1h0ZM71.8,27.4h-2.3c-1.3,0-2.3-1-2.3-2.3s1-2.3,2.3-2.3h6.9c0,2.5-2,4.6-4.6,4.6h0Z'/%3e%3cpath%20d='M52.3,9.1h-4.6V0h-4.6V32h9.1c5,0,9.1-4.1,9.1-9.1v-4.6c0-5.1-4.1-9.1-9.1-9.1h0ZM56.9,22.9c0,2.5-2,4.6-4.6,4.6h-4.6v-13.7h4.6c2.5,0,4.6,2,4.6,4.6v4.6h0Z'/%3e%3cpath%20d='M110.9,13.7h9.1v-4.6h-9.1c-5.1,0-9.1,4.1-9.1,9.1v4.6c0,5.1,4.1,9.1,9.1,9.1h9.1v-4.6h-9.1c-2.5,0-4.6-2-4.6-4.6h13.7v-4.6h-13.7c0-2.5,2-4.6,4.6-4.6h0Z'/%3e%3cpath%20d='M93.6,18.3h-4.6c-1.3,0-2.3-1-2.3-2.3s1-2.3,2.3-2.3h10.3v-4.6h-10.3c-3.8,0-6.9,3.1-6.9,6.9s3.1,6.9,6.9,6.9h4.6c1.3,0,2.3,1,2.3,2.3s-1,2.3-2.3,2.3h-10.3v4.6h10.3c3.8,0,6.9-3.1,6.9-6.9s-3.1-6.9-6.9-6.9Z'/%3e%3c/g%3e%3c/g%3e%3c/svg%3e)
AIbase是一个专注于MCP服务的平台，为AI开发者提供高质量的模型上下文协议服务，助力AI应用开发。
简体中文