AI 模型库
Qwen2-VL-7B-Instruct
image-text-to-textWe're excited to unveil **Qwen2-VL**, the latest iteration of our Qwen-VL model, representing nearly a year of innovation.
nsfw-image-detection-large
🚀 FocalNet NSFW图像分类器：您的内容审核超级英雄！🦸♂️
gemma-4-E2B-it
any-to-anyHugging Face | GitHub | Launch Blog | Documentation License: Apache 2.0 | Authors: Google DeepMind
Qwen2.5-VL-3B-Instruct
image-text-to-text许可证名称：qwen-research 许可证链接：https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/LICENSE 语言： - 英语 流水线标签：图像-文本到文本 标签： - 多模态 库名称：transformers
gemma-4-26B-A4B-it-GGUF
image-text-to-textSee Unsloth Dynamic 2.0 GGUFs for our quantization benchmarks.
Qwen3.6-27B-FP8
image-text-to-text> [!Note] > This repository contains FP8-quantized model weights and configuration files for the post-trained model in the Hugging Face Transformers format. > > These artifacts are compatible with Hu
Qwen3.5-27B
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
Qwen3-1.7B
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
twitter-roberta-base-sentiment-latest
text-classification用于情感分析的Twitter-roBERTa-base模型 - 已更新（2022）
CLIP-ViT-B-32-laion2B-s34B-b79K
zero-shot-image-classification1. Model Details 2. Uses 3. Training Details 4. Evaluation 5. Acknowledgements 6. Citation 7. How To Get Started With the Model
Gemma-3-1B-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking_GGUF
text-generation--- license: gemma language: - en base_model: - google/gemma-3-1b-it tags: - uncensored - text-generation - reasoning - instruction-tuned - lightweight --- Gemma 3 – 1B IT GLM-4.7 Flash
Meta-Llama-3-8B
text-generationtext-generation
dinov2-base
image-feature-extractionVision Transformer (base-sized model) trained using DINOv2
koelectra-small-v3-nsmc
text-classification情感二分类（基于KoELECTRA-Small-v3模型与Naver情感电影语料库数据集的微调）
w2v-bert-2.0
feature-extraction我们正在开源基于Conformer的W2v-BERT 2.0语音编码器，如论文第3.2.1节所述，该编码器是我们Seamless模型的核心。
table-transformer-detection
object-detection基于PubTables1M数据集训练的Table Transformer（DETR）模型。该模型由Smock等人在论文《PubTables-1M: Towards Comprehensive Table Extraction From Unstructured Documents》中提出，并首次在此仓库中发布。
convnextv2_nano.fcmae_ft_in22k_in1k
image-classificationA ConvNeXt-V2 image classification model. Pretrained with a fully convolutional masked autoencoder framework (FCMAE) and fine-tuned on ImageNet-22k and then ImageNet-1k.
mobilevit-small
image-classificationMobileViT model pre-trained on ImageNet-1k at resolution 256x256. It was introduced in MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer by Sachin Mehta and Mohammad Ras
pythia-160m
text-generation*Pythia Scaling Suite* 是一组为促进可解释性研究而开发的模型集合（详见论文）。该套件包含两组共八个模型，参数量分别为70M、160M、410M、1B、1.4B、2.8B、6.9B和12B。每个参数量对应两个模型：一个在Pile数据集上训练，另一个在P
jina-embeddings-v3
feature-extractionjina-embeddings-v3: Multilingual Embeddings With Task LoRA