AI 模型库
Qwen2.5-VL-7B-Instruct
image-text-to-text许可证：apache-2.0 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
bge-base-en-v1.5
feature-extractionModel List | FAQ | Usage | Evaluation | Train | Contact | Citation | License
opt-125m
text-generationOPT 首次在《开放预训练Transformer语言模型》中被提出，并于2022年5月3日由Meta AI在metaseq的代码库中首次发布。
unidepth-v2-vitl14
该模型已通过PytorchModelHubMixin集成推送至Hub： - 库：https://github.com/lpiccinelli-eth/UniDepth - 文档：[需要更多信息]
XTTS-v2
text-to-speechⓍTTS ⓍTTS 是一款语音生成模型，仅需一段6秒的音频片段，即可将声音克隆到不同语言中。无需依赖长达数小时的庞大数据进行训练。
Qwen3.5-9B
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
GLM-OCR
image-to-text👋 Join our WeChat and Discord community 📍 Use GLM-OCR's API 👉 GLM-OCR SDK Recommended 📖 Technical Report
chronos-bolt-small
time-series-forecasting🚀 **Update Feb 14, 2025**: Chronos-Bolt models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lin
contriever
该模型采用《Towards Unsupervised Dense Information Retrieval with Contrastive Learning》中描述的方法进行无监督训练。相关GitHub代码仓库可通过以下链接访问：https://github.com/facebookresearch/contriever。
multilingual-e5-small
sentence-similarity多语言E5文本嵌入：技术报告。 王亮、杨楠、黄小龙、杨林军、Rangan Majumder、韦福如，arXiv 2024
nomic-embed-text-v1
sentence-similaritynomic-embed-text-v1：一种可复现的长上下文（8192）文本嵌入器
chronos-bolt-base
time-series-forecasting🚀 **Update Feb 14, 2025**: Chronos-Bolt models are now available on Amazon SageMaker JumpStart! Check out the tutorial notebook to learn how to deploy Chronos endpoints for production use in a few lin
multilingual-e5-large
feature-extraction多语言E5文本嵌入：技术报告。 王亮、杨楠、黄小龙、杨林军、Rangan Majumder、韦福如，arXiv 2024
gpt-oss-20b
text-generationTry gpt-oss · Guides · Model card · OpenAI blog
gemma-4-26B-A4B-it
image-text-to-textHugging Face | GitHub | Launch Blog | Documentation License: Apache 2.0 | Authors: Google DeepMind
xlm-roberta-large
fill-maskXLM-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。
Llama-3.2-1B-Instruct
text-generationtext-generation
whisper-large-v3-turbo
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
finbert
text-classificationFinBERT是一种预训练的自然语言处理模型，用于分析金融文本的情感倾向。它通过在金融领域进一步训练BERT语言模型构建而成，利用大规模金融语料库进行微调，从而实现对金融情感的分类。Malo等人（2014）提出的金融短语库（Financial PhraseBank）被用于
tiny-Qwen2ForCausalLM-2.5
text-generation这是一个为TRL库中的单元测试构建的最小模型。