AI 模型库
fairface_age_image_detection
image-classificationDetects age group with about 59% accuracy based on an image.
Qwen3.5-4B
image-text-to-text> [!Note] > This repository contains model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hugging Face Tra
DFN5B-CLIP-ViT-H-14-378
一个在DFN-5B上训练的CLIP（对比语言-图像预训练）模型。 数据过滤网络（DFN）是用于自动过滤大规模未整理数据池的小型网络。 该模型基于从430亿未整理图文对（128亿图像）中筛选出的50亿张图像进行训练。
paraphrase-multilingual-mpnet-base-v2
sentence-similaritysentence-transformers/paraphrase-multilingual-mpnet-base-v2
Qwen3-32B
text-generationQwen3 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
chronos-2
time-series-forecastingChronos-2 **Chronos-2** is a 120M-parameter, encoder-only time series foundation model for zero-shot forecasting. It supports **univariate**, **multivariate**, and **covariate-informed** tasks within
Wan_2.2_ComfyUI_Repackaged
示例：https://comfyanonymous.github.io/ComfyUI_examples/wan22/
Qwen2.5-0.5B-Instruct
text-generationQwen2.5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。与Qwen2相比，Qwen2.5带来了以下改进：
Qwen3-Embedding-0.6B
feature-extractionThe Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen
WanVideo_comfy
WanVideo的合并与量化模型，源自此处：
gemma-4-E4B-it
any-to-anyHugging Face | GitHub | Launch Blog | Documentation License: Apache 2.0 | Authors: Google DeepMind
Qwen3-VL-8B-Instruct
image-text-to-textMeet Qwen3-VL — the most powerful vision-language model in the Qwen series to date.
whisper-large-v3
automatic-speech-recognitionWhisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation, proposed in the paper Robust Speech Recognition via Large-Scale Weak Supervision by Alec Radford et
segmentation
voice-activity-detection语音活动检测
vit-base-patch16-224
image-classificationVision Transformer (ViT) model pre-trained on ImageNet-21k (14 million images, 21,843 classes) at resolution 224x224, and fine-tuned on ImageNet 2012 (1 million images, 1,000 classes) at resolution 22
dolphin-2.9.1-yi-1.5-34b
text-generation由Eric Hartford、Lucas Atkins、Fernando Fernandes及Cognitive Computations共同策划并训练
bert-base-multilingual-cased
fill-mask基于掩码语言建模（MLM）目标，在维基百科规模最大的前104种语言上预训练的模型。该模型首次发表于此论文，并在此仓库中首次发布。此模型区分大小写：例如，它能够识别"english"与"English"之间的差异。
Qwen2-1.5B-Instruct
text-generationQwen2是Qwen大语言模型系列的新版本。针对Qwen2，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，其中包括一个混合专家模型。本仓库包含指令微调后的15亿参数Qwen2模型。
mxbai-embed-large-v1
feature-extractionThe crispy sentence embedding family from Mixedbread.
gpt-oss-120b
text-generationTry gpt-oss · Guides · Model card · OpenAI blog