AI 模型库

共 个模型
下载量 收藏数 最新

all-MiniLM-L6-v2

sentence-similarity
sentence-transformers · sentence-transformers/all-MiniLM-L6-v2

all-MiniLM-L6-v2 这是一个句子变换器模型：它将句子和段落映射到384维的稠密向量空间，可用于聚类或语义搜索等任务。

252,520,628 4982

Qwen3-VL-2B-Instruct

image-text-to-text
Qwen · Qwen/Qwen3-VL-2B-Instruct

Meet Qwen3-VL — 迄今为止通义千问系列中最强大的视觉语言模型。

187,009,049 586

bert-base-uncased

fill-mask
google-bert · google-bert/bert-base-uncased

基于掩码语言建模（MLM）目标在英语上预训练的模型。该模型首次发表于此论文，并首次在此仓库中发布。此模型不区分大小写：即对"english"和"English"不作区分。

62,660,343 2836

electra-base-discriminator

google · google/electra-base-discriminator

ELECTRA：以判别器而非生成器方式预训练文本编码器

54,079,034 299

paraphrase-multilingual-MiniLM-L12-v2

sentence-similarity
sentence-transformers · sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2

46,703,265 1424

ms-marco-MiniLM-L6-v2

text-ranking
cross-encoder · cross-encoder/ms-marco-MiniLM-L6-v2

该模型在MS Marco段落排序任务上进行了训练。

45,928,464 412

bge-small-en-v1.5

feature-extraction
BAAI · BAAI/bge-small-en-v1.5

Model List | FAQ | Usage | Evaluation | Train | Contact | Citation | License

38,647,692 645

all-mpnet-base-v2

sentence-similarity
sentence-transformers · sentence-transformers/all-mpnet-base-v2

all-mpnet-base-v2 这是一个句子变换器模型：它将句子和段落映射到768维的稠密向量空间，可用于聚类或语义搜索等任务。

36,263,119 1508

clip-vit-large-patch14

zero-shot-image-classification
openai · openai/clip-vit-large-patch14

Disclaimer: The model card is taken and modified from the official CLIP repository, it can be found here.

27,909,208 2200

bge-m3

sentence-similarity
BAAI · BAAI/bge-m3

更多详情请参考我们的GitHub仓库：https://github.com/FlagOpen/FlagEmbedding

22,848,282 3184

clip-vit-base-patch32

zero-shot-image-classification
openai · openai/clip-vit-base-patch32

Disclaimer: The model card is taken and modified from the official CLIP repository, it can be found here.

21,453,525 1139

clap-htsat-fused

audio-classification
laion · laion/clap-htsat-fused

Model card for CLAP: Contrastive Language-Audio Pretraining

20,041,593 283

roberta-large

fill-mask
FacebookAI · FacebookAI/roberta-large

--- language: en tags: - exbert license: mit datasets: - bookcorpus - wikipedia --- RoBERTa 大型模型 基于掩码语言建模（MLM）目标在英语上预训练的模型。该模型首次在 此论文中提出，并在此仓库中首次发布。此模型区分大小写。

19,837,112 486

xlm-roberta-base

fill-mask
FacebookAI · FacebookAI/xlm-roberta-base

XLM-RoBERTa模型在包含100种语言的2.5TB过滤CommonCrawl数据上进行了预训练。该模型由Conneau等人在论文《大规模无监督跨语言表示学习》中提出，并首次在此仓库中发布。

19,384,446 1026

mobilenetv3_small_100.lamb_in1k

image-classification
timm · timm/mobilenetv3_small_100.lamb_in1k

A MobileNet-v3 image classification model. Trained on ImageNet-1k in `timm` using recipe template described below.

18,655,969 288

Qwen3-0.6B

text-generation
Qwen · Qwen/Qwen3-0.6B

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groun

18,271,115 1452

roberta-base

fill-mask
FacebookAI · FacebookAI/roberta-base

基于遮蔽语言建模（MLM）目标在英语上预训练的模型。该模型首次发表于 此论文，并首次发布于 此仓库。此模型区分大小写：它 能识别english与English之间的差异。

18,091,809 805

chronos-2

time-series-forecasting
amazon · amazon/chronos-2

**Update Dec 30, 2025:** ☁️ Deploy Chronos-2 on Amazon SageMaker. New guide covers real-time GPU and CPU inference, serverless endpoints (run on demand, no idle costs), and batch transform for large-s

17,696,259 455

distilbert-base-uncased

fill-mask
distilbert · distilbert/distilbert-base-uncased

该模型是BERT基础模型的蒸馏版本。该模型首次发表于此论文中。蒸馏过程的代码可在此处获取。该模型不区分大小写：它不会区分"english"和"English"。

16,186,558 1073

gpt2

text-generation
openai-community · openai-community/gpt2

在此处测试整体生成能力：https://transformer.huggingface.co/doc/gpt2-large

15,977,391 3413
1 2 3 4 ... 10