模型介绍
内容详情
替代品
模型简介
该模型主要用于信息检索任务，能够高效地从大规模数据集中检索相关文档或答案。
模型特点
高效检索
在多个标准数据集上表现出色，具备高效的检索能力。
多数据集支持
在 MTEB ArguAna 和 CQADupstackAndroidRetrieval 等多个数据集上进行了评估。
模型能力
信息检索
文档匹配
使用案例
信息检索
问答系统
用于构建问答系统，快速检索相关答案。
在 MTEB ArguAna 数据集上达到 68.277 的主要得分。
文档检索
用于从大规模文档库中检索相关文档。
在 CQADupstackAndroidRetrieval 数据集上达到 57.025 的主要得分。
model-index:
- name: NV-Retriever-v1
results:
- dataset:
config: default
name: MTEB ArguAna
revision: c22ab2a51041ffd869aaddef7af8d8215647e41a
split: test
type: mteb/arguana
metrics:
- type: main_score value: 68.277
- type: map_at_1 value: 44.666
- type: map_at_10 value: 60.3
- type: map_at_100 value: 60.692
- type: map_at_1000 value: 60.693
- type: map_at_20 value: 60.645
- type: map_at_3 value: 56.472
- type: map_at_5 value: 58.78
- type: mrr_at_1 value: 45.092460881934564
- type: mrr_at_10 value: 60.493378717063074
- type: mrr_at_100 value: 60.87988588545791
- type: mrr_at_1000 value: 60.88044591502747
- type: mrr_at_20 value: 60.83224958805471
- type: mrr_at_3 value: 56.53153153153162
- type: mrr_at_5 value: 58.942626837363854
- type: nauc_map_at_1000_diff1 value: 14.137909741937149
- type: nauc_map_at_1000_max value: -13.946656236190021
- type: nauc_map_at_1000_std value: -27.431659737602732
- type: nauc_map_at_100_diff1 value: 14.136483238553824
- type: nauc_map_at_100_max value: -13.946721068575075
- type: nauc_map_at_100_std value: -27.43462339510713
- type: nauc_map_at_10_diff1 value: 13.961240252441984
- type: nauc_map_at_10_max value: -13.804526866049605
- type: nauc_map_at_10_std value: -27.35573153559941
- type: nauc_map_at_1_diff1 value: 16.257792463128126
- type: nauc_map_at_1_max value: -16.164790771610072
- type: nauc_map_at_1_std value: -27.84021734986689
- type: nauc_map_at_20_diff1 value: 14.106499894575682
- type: nauc_map_at_20_max value: -13.930699708027205
- type: nauc_map_at_20_std value: -27.47446428876476
- type: nauc_map_at_3_diff1 value: 15.018611065750246
- type: nauc_map_at_3_max value: -12.659774043658842
- type: nauc_map_at_3_std value: -27.186079034885598
- type: nauc_map_at_5_diff1 value: 14.199306816408377
- type: nauc_map_at_5_max value: -13.261282961741303
- type: nauc_map_at_5_std value: -26.71739573072423
- type: nauc_mrr_at_1000_diff1 value: 12.629073492081275
- type: nauc_mrr_at_1000_max value: -14.666344334069448
- type: nauc_mrr_at_1000_std value: -27.30760238816266
- type: nauc_mrr_at_100_diff1 value: 12.627677268171094
- type: nauc_mrr_at_100_max value: -14.66639461039424
- type: nauc_mrr_at_100_std value: -27.310569102264846
- type: nauc_mrr_at_10_diff1 value: 12.482407364331927
- type: nauc_mrr_at_10_max value: -14.509649052862667
- type: nauc_mrr_at_10_std value: -27.246235066954423
- type: nauc_mrr_at_1_diff1 value: 15.084265144497373
- type: nauc_mrr_at_1_max value: -16.312295398834625
- type: nauc_mrr_at_1_std value: -27.686736137340894
- type: nauc_mrr_at_20_diff1 value: 12.600281810712003
- type: nauc_mrr_at_20_max value: -14.649133303237166
- type: nauc_mrr_at_20_std value: -27.350630544847004
- type: nauc_mrr_at_3_diff1 value: 13.081208137779557
- type: nauc_mrr_at_3_max value: -13.91769455651833
- type: nauc_mrr_at_3_std value: -27.42237181201488
- type: nauc_mrr_at_5_diff1 value: 12.697412153053486
- type: nauc_mrr_at_5_max value: -14.046815225580204
- type: nauc_mrr_at_5_std value: -26.69417403787157
- type: nauc_ndcg_at_1000_diff1 value: 13.984706619459738
- type: nauc_ndcg_at_1000_max value: -13.48207980711916
- type: nauc_ndcg_at_1000_std value: -27.16935912553381
- type: nauc_ndcg_at_100_diff1 value: 13.951491624929446
- type: nauc_ndcg_at_100_max value: -13.483812067015261
- type: nauc_ndcg_at_100_std value: -27.238639718923814
- type: nauc_ndcg_at_10_diff1 value: 13.16429886726646
- type: nauc_ndcg_at_10_max value: -12.816570276390305
- type: nauc_ndcg_at_10_std value: -27.13129457560619
- type: nauc_ndcg_at_1_diff1 value: 16.257792463128126
- type: nauc_ndcg_at_1_max value: -16.164790771610072
- type: nauc_ndcg_at_1_std value: -27.84021734986689
- type: nauc_ndcg_at_20_diff1 value: 13.767660163849325
- type: nauc_ndcg_at_20_max value: -13.330392545127982
- type: nauc_ndcg_at_20_std value: -27.655874185287637
- type: nauc_ndcg_at_3_diff1 value: 15.379454570465107
- type: nauc_ndcg_at_3_max value: -10.682369832384417
- type: nauc_ndcg_at_3_std value: -26.61546503103021
- type: nauc_ndcg_at_5_diff1 value: 13.857194107241847
- type: nauc_ndcg_at_5_max value: -11.585582001386438
- type: nauc_ndcg_at_5_std value: -25.60318972329879
- type: nauc_precision_at_1000_diff1 value: 25.196544697410012
- type: nauc_precision_at_1000_max value: 20.85546049013785
- type: nauc_precision_at_1000_std value: 56.11900085120013
- type: nauc_precision_at_100_diff1 value: 11.605921153386918
- type: nauc_precision_at_100_max value: 14.521201087528956
- type: nauc_precision_at_100_std value: 17.78762614096395
- type: nauc_precision_at_10_diff1 value: 2.9073450747110328
- type: nauc_precision_at_10_max value: -1.7706065742373982
- type: nauc_precision_at_10_std value: -25.127721917434958
- type: nauc_precision_at_1_diff1 value: 16.257792463128126
- type: nauc_precision_at_1_max value: -16.164790771610072
- type: nauc_precision_at_1_std value: -27.84021734986689
- type: nauc_precision_at_20_diff1 value: 4.945029151806525
- type: nauc_precision_at_20_max value: 1.299254371223885
- type: nauc_precision_at_20_std value: -42.34878406902393
- type: nauc_precision_at_3_diff1 value: 17.02535492673917
- type: nauc_precision_at_3_max value: -3.160620615377462
- type: nauc_precision_at_3_std value: -24.392959569235646
- type: nauc_precision_at_5_diff1 value: 12.283704585525927
- type: nauc_precision_at_5_max value: -2.860819740357931
- type: nauc_precision_at_5_std value: -19.497494992596568
- type: nauc_recall_at_1000_diff1 value: 25.196544697407973
- type: nauc_recall_at_1000_max value: 20.855460490135933
- type: nauc_recall_at_1000_std value: 56.119000851196496
- type: nauc_recall_at_100_diff1 value: 11.60592115338627
- type: nauc_recall_at_100_max value: 14.5212010875248
- type: nauc_recall_at_100_std value: 17.787626140957425
- type: nauc_recall_at_10_diff1 value: 2.9073450747112304
- type: nauc_recall_at_10_max value: -1.7706065742371515
- type: nauc_recall_at_10_std value: -25.12772191743481
- type: nauc_recall_at_1_diff1 value: 16.257792463128126
- type: nauc_recall_at_1_max value: -16.164790771610072
- type: nauc_recall_at_1_std value: -27.84021734986689
- type: nauc_recall_at_20_diff1 value: 4.9450291518064935
- type: nauc_recall_at_20_max value: 1.2992543712237186
- type: nauc_recall_at_20_std value: -42.34878406902303
- type: nauc_recall_at_3_diff1 value: 17.025354926739237
- type: nauc_recall_at_3_max value: -3.1606206153775016
- type: nauc_recall_at_3_std value: -24.39295956923558
- type: nauc_recall_at_5_diff1 value: 12.283704585525939
- type: nauc_recall_at_5_max value: -2.8608197403578512
- type: nauc_recall_at_5_std value: -19.497494992596575
- type: ndcg_at_1 value: 44.666
- type: ndcg_at_10 value: 68.277
- type: ndcg_at_100 value: 69.78
- type: ndcg_at_1000 value: 69.78999999999999
- type: ndcg_at_20 value: 69.464
- type: ndcg_at_3 value: 60.462
- type: ndcg_at_5 value: 64.651
- type: precision_at_1 value: 44.666
- type: precision_at_10 value: 9.339
- type: precision_at_100 value: 0.996
- type: precision_at_1000 value: 0.1
- type: precision_at_20 value: 4.897
- type: precision_at_3 value: 24.016000000000002
- type: precision_at_5 value: 16.458000000000002
- type: recall_at_1 value: 44.666
- type: recall_at_10 value: 93.38499999999999
- type: recall_at_100 value: 99.57300000000001
- type: recall_at_1000 value: 99.644
- type: recall_at_20 value: 97.937
- type: recall_at_3 value: 72.048
- type: recall_at_5 value: 82.28999999999999 task: type: Retrieval
- dataset:
config: default
name: MTEB CQADupstackAndroidRetrieval
revision: f46a197baaae43b4f621051089b82a364682dfeb
split: test
type: mteb/cqadupstack-android
metrics:
- type: main_score value: 57.025000000000006
- type: map_at_1 value: 35.67
- type: map_at_10 value: 49.816
- type: map_at_100 value: 51.465
- type: map_at_1000 value: 51.559
- type: map_at_20 value: 50.843
- type: map_at_3 value: 45.462
- type: map_at_5 value: 47.789
- type: mrr_at_1 value: 44.77825464949928
- type: mrr_at_10 value: 55.787576356245886
- type: mrr_at_100 value: 56.4488799265231
- type: mrr_at_1000 value: 56.47353697784773
- type: mrr_at_20 value: 56.21107253216036
- type: mrr_at_3 value: 52.885073915116834
- type: mrr_at_5 value: 54.58035288507389
- type: nauc_map_at_1000_diff1 value: 50.45823101819382
- type: nauc_map_at_1000_max value: 36.49053295534483
- type: nauc_map_at_1000_std
- dataset:
config: default
name: MTEB ArguAna
revision: c22ab2a51041ffd869aaddef7af8d8215647e41a
split: test
type: mteb/arguana
metrics:
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