AI 模型库

共 个模型
下载量 收藏数 最新

nomic-embed-text-v1.5

sentence-similarity
nomic-ai · nomic-ai/nomic-embed-text-v1.5

nomic-embed-text-v1.5：基于套娃表示学习的可伸缩生产级嵌入模型

15,837,783 1050

adetailer

Bingsu · Bingsu/adetailer

- coco2017（仅人物） - AniSeg - skytnt/anime-segmentation

15,501,796 881

nsfw_image_detection

image-classification
Falconsai · Falconsai/nsfw_image_detection

Model Card: Fine-Tuned Vision Transformer (ViT) for NSFW Image Classification

15,384,704 1266

colbertv2.0

colbert-ir · colbert-ir/colbertv2.0

ColBERT is a _fast_ and _accurate_ retrieval model, enabling scalable BERT-based search over large text collections in tens of milliseconds.

15,378,174 509

bge-large-en-v1.5

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

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

15,307,823 864

Qwen2.5-7B-Instruct

text-generation
Qwen · Qwen/Qwen2.5-7B-Instruct

Qwen2.5 is the latest series of Qwen large language models. For Qwen2.5, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters. Qw

14,018,215 1441

Qwen2.5-1.5B-Instruct

text-generation
Qwen · Qwen/Qwen2.5-1.5B-Instruct

Qwen2.5是Qwen大语言模型的最新系列。针对Qwen2.5，我们发布了一系列基础语言模型和指令微调语言模型，参数量从0.5亿到720亿不等。相较于Qwen2，Qwen2.5带来了以下改进：

12,078,264 900

Qwen3-8B

text-generation
Qwen · Qwen/Qwen3-8B

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

11,444,026 1264

DeepSeek-V3.2

text-generation
deepseek-ai · deepseek-ai/DeepSeek-V3.2

<!-- markdownlint-disable first-line-h1 --> <!-- markdownlint-disable html --> <!-- markdownlint-disable no-duplicate-header -->

11,120,947 1621

whisperkit-coreml

automatic-speech-recognition
argmaxinc · argmaxinc/whisperkit-coreml

--- pretty_name: "WhisperKit" viewer: false library_name: whisperkit tags: - whisper - whisperkit - coreml - asr - quantized - automatic-speech-recognition --- WhisperKit

10,910,125 388

wespeaker-voxceleb-resnet34-LM

pyannote · pyannote/wespeaker-voxceleb-resnet34-LM

在生产环境中使用这个开源模型？ 考虑切换到 pyannoteAI 以获得更优、更快的选择。

10,855,696 320

Qwen3-4B-Instruct-2507

text-generation
Qwen · Qwen/Qwen3-4B-Instruct-2507

We introduce the updated version of the **Qwen3-4B non-thinking mode**, named **Qwen3-4B-Instruct-2507**, featuring the following key enhancements:

10,724,588 1049

bge-reranker-v2-m3

text-classification
BAAI · BAAI/bge-reranker-v2-m3

更多详情请参考我们的Github：FlagEmbedding。

10,688,225 1201

speaker-diarization-3.1

automatic-speech-recognition
pyannote · pyannote/speaker-diarization-3.1

自动语音识别

10,249,640 2057

segmentation-3.0

voice-activity-detection
pyannote · pyannote/segmentation-3.0

语音活动检测

10,016,318 1153

clip-vit-large-patch14-336

zero-shot-image-classification
openai · openai/clip-vit-large-patch14-336

<!-- This model card has been generated automatically according to the information Keras had access to. You should probably proofread and complete it, then remove this comment. -->

9,641,107 515

Kokoro-82M

text-to-speech
hexgrad · hexgrad/Kokoro-82M

**Kokoro** 是一个拥有8200万参数的开源权重文本转语音（TTS）模型。尽管其架构轻量，但能提供与更大模型相媲美的质量，同时速度显著更快、成本效益更高。凭借Apache许可证授权的权重，Kokoro可部署于从生产环境到各类应用场景。

9,623,959 6303

Llama-3.1-8B-Instruct

text-generation
meta-llama · meta-llama/Llama-3.1-8B-Instruct

text-generation

9,374,277 5994

gemma-4-31B-it

image-text-to-text
google · google/gemma-4-31B-it

Hugging Face | GitHub | Launch Blog | Documentation License: Apache 2.0 | Authors: Google DeepMind

8,965,984 2809

Qwen2.5-3B-Instruct

text-generation
Qwen · Qwen/Qwen2.5-3B-Instruct

Qwen2.5是Qwen大语言模型的最新系列。针对Qwen2.5，我们发布了从0.5到720亿参数规模的多个基础语言模型和指令微调语言模型。相较于Qwen2，Qwen2.5带来了以下改进：

8,755,192 656
1 2 3 4 5 ... 10