登录

transformers.js

huggingfaceApache-2.0活跃维护

在浏览器里直接跑 Hugging Face 的 Transformer 模型，不用后端服务器，前端就能做文本、视觉等机器学习推理。

State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!

4.3.2发布于 2026-10-28 02:23 UTC16,408star +3 / 7 天1,229fork同步于 2026-11-10 05:24 UTC
浏览器推理前端机器学习TransformerWebMLJavaScript
对比 GitHub 官网browserjavascripttransformerswebml

怎么上手

由 README 提炼，执行前请确认
原文 
npm i @huggingface/transformers
硬件要求按 README 说明

默认在浏览器通过 WASM 用 CPU 运行；设置 device: 'webgpu' 可改用 GPU（WebGPU）。README 未给出显存或具体 GPU 型号要求。

下载：源码 zip·GitHub Releases（安装包）本站不镜像安装包

项目说明

由 README 自动翻译提炼
没人工点评？写下你的经验

在浏览器里直接跑 Hugging Face 预训练模型的 JS 库，无需服务器

在浏览器里直接跑 Hugging Face 的 Transformer 模型，不用后端服务器，前端就能做文本、视觉等机器学习推理。

核心能力

  • 用 pipeline API 一行调用预训练模型
  • 基于 ONNX Runtime 在浏览器执行推理
  • 默认走 WASM 用 CPU，可切 WebGPU 用 GPU
  • 支持 NLP、视觉、音频、多模态多类任务
  • 用 dtype 选项做 q8/q4 量化降低带宽

容易踩的坑

首次运行会从 Hugging Face Hub 下载模型，需联网或自行配置本地模型路径；WebGPU 在多数浏览器仍属实验特性，可能报错；WASM 二进制默认从 CDN 加载，离线部署需改 env.backends.onnx.wasm.wasmPaths。

内容由模型根据 README 生成，可能不完整或不准确，以官方文档为准。看原文 README

最近发版

5 个版本4.3.2
全部 release
  1. 4.3.2最新正式版2026-10-28 · 2026-10-28 02:23 UTC

    What's new?

    New contributors

    Full Changelog: https://github.com/huggingface/transformers.js/compare/4.3.1...4.3.2

  2. 4.3.12026-10-07 · 2026-10-07 03:19 UTC
    查看更新说明

    What's new?

    This release adds support for EmbeddingGemma 2. EmbeddingGemma 2 is an open multimodal embedding model built by Google DeepMind which maps text (incl. code), images, video, and audio inputs—and combinations thereof—into a single, unified 768-dimensional vector space. The model has 740M total parameters, combining a 270M parameter text model with modular vision (170M) and audio (300M) encoders.

    Text search

    The feature-extraction pipeline returns normalized embeddings, so the dot product of two embeddings is their cosine similarity:

    import { pipeline, matmul } from "@huggingface/transformers";

const extractor = await pipeline("feature-extraction", "onnx-community/embeddinggemma-2-ONNX", {
  device: "webgpu", // or "wasm" (browser) / "cpu" (Node.js)
  dtype: "q4", // see "Choosing a dtype" below
});

const query = "task: search result | query: Which planet is known as the Red Planet?";
const documents = [
  "title: none | text: Venus is often called Earth's twin because of its similar size and proximity.",
  "title: none | text: Mars, known for its reddish appearance, is often referred to as the Red Planet.",
  "title: none | text: Jupiter, the largest planet in our solar system, has a prominent red spot.",
  "title: none | text: Saturn, famous for its rings, is sometimes mistaken for the Red Planet.",
];

const embeddings = await extractor([query, ...documents], { pooling: "mean", normalize: true });
const query_embedding = embeddings.slice([0, 1]);
const document_embeddings = embeddings.slice([1, null]);

const scores = (await matmul(query_embedding, document_embeddings.transpose(1, 0))).tolist()[0];
const ranking = scores.map((score, i) => ({ score, document: documents[i] })).sort((a, b) => b.score - a.score);
console.log(ranking);
// [
//   { score: 0.854, document: "title: none | text: Mars, known for its reddish appearance, ..." },
//   { score: 0.783, document: "title: none | text: Saturn, famous for its rings, ..." },
//   { score: 0.752, document: "title: none | text: Jupiter, the largest planet in our solar system, ..." },
//   { score: 0.684, document: "title: none | text: Venus is often called Earth's twin, ..." },
// ]

    Images, audio and video

    For other modalities, use the processor and the model directly. Every input maps into the same embedding space, so any embedding can be compared with any other: here, text queries against an image, an audio clip and a video.

    import { AutoModel, AutoProcessor, load_image, load_audio, load_video, cat, matmul } from "@huggingface/transformers";

const model_id = "onnx-community/embeddinggemma-2-ONNX";
const processor = await AutoProcessor.from_pretrained(model_id);
const model = await AutoModel.from_pretrained(model_id, { device: "webgpu", dtype: "q4" });

// The processor takes (text, images, audio, videos)
const embed = async (...inputs) => (await model(await processor(...inputs))).sentence_embedding;

// Text queries, with a task prefix (see "Task Instruction Prefixes" below)
const queries = [
  "task: search result | query: cats sleeping on a couch",
  "task: search result | query: a president's speech about serving your country",
  "task: search result | query: a turtle swimming in the ocean",
];
const query_embeddings = await embed(queries);

// An image, an audio clip (mono, 16 kHz) and a video (1 frame per second)
const url = "https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main";
const image = await load_image(`${url}/cats.jpg`);
const audio = await load_audio(`${url}/jfk.wav`, 16000);
const video = await load_video(`${url}/sea-turtle.mp4`, { fps: 1 });

const media_embeddings = cat([
  await embed(null, image),
  await embed(null, null, audio),
  await embed(null, null, null, video),
]);

// Embeddings are normalized: the dot product is the cosine similarity
const
  3. 4.3.02026-09-16 · 2026-09-16 05:13 UTC
    查看更新说明

    🚀 Transformers.js v4.3 — Structured Output, New Models, WebGPU upgrade, Documentation Overhaul

    This release adds structured output, three new model architectures, WebGPU support for Safari 26+, and a documentation overhaul. We also upgraded ONNX Runtime to the latest version.

    What's new?

    Structured output

    Constrain generation to a JSON schema, JSON object, or regular expression with the experimental, dependency-free @huggingface/transformers-structured-output package in https://github.com/huggingface/transformers.js/pull/1758.

    For example, classify customer feedback into a fixed set of sentiments and topics:

    import { pipeline, TextStreamer } from "@huggingface/transformers";
import { StructuredOutputProcessor } from "@huggingface/transformers-structured-output";

// Create the pipeline first so its tokenizer is available.
const generator = await pipeline(
  "text-generation",
  "onnx-community/LFM2.5-350M-ONNX",
  { dtype: "q4f16", device: "webgpu" },
);

const processor = new StructuredOutputProcessor(generator.tokenizer, {
  type: "json_schema",
  json_schema: {
    type: "object",
    properties: {
      sentiment: { enum: ["positive", "negative", "neutral"] },
      topic: { enum: ["price", "quality", "delivery", "other"] },
    },
    required: ["sentiment", "topic"],
    additionalProperties: false,
  },
});

const messages = [
  {
    role: "user",
    content: "Classify this feedback: The product is way too expensive.",
  },
];

const output = await generator(messages, {
  max_new_tokens: 512,
  do_sample: false,
  streamer: new TextStreamer(generator.tokenizer, {
    skip_prompt: true,
    skip_special_tokens: true,
  }),
  logits_processor: [processor],
});

console.log(output[0].generated_text.at(-1).content);
// {"sentiment": "negative", "topic": "price"}

    Currently supports one generated sequence at a time. Set a sufficient token budget so the output can finish.

    New models

    Browser and storage improvements

    Fixes

  4. 4.2.02026-04-23 · 2026-04-23 12:49 UTC
    查看更新说明

    🚀 Transformers.js v4.2 — Tool calling, simpler internals, and privacy filtering

    • Added tools to TextGenerationPipeline in #1655
    • Use inputMetadata API for simplified internals in #1657
    • Add support for OpenAI privacy filter model in #1658

    Full Changelog: 4.1.0...4.2.0

  5. 4.1.02026-04-23 · 2026-04-23 12:49 UTC
    查看更新说明

    🚀 Transformers.js v4.1 — Gemma 4, KV cache improvements, and new quantization dtypes

    • Add support for Gemma 4 in #1627
    • Cached generation improvements (+ past_key_values via pipeline function) in #1638
    • Improve tokenizer types based on input function parameters in #1641
    • Add support for q1, q1f16, q2, and q2f16 data types in #1647
    • Re-enable SmolVLM in #1648
    • Update default generation parameters in #1649
    • Pin GitHub Actions to commit SHAs in #1626

    Full Changelog: 4.0.0...4.1.0

用户点评

登录用户的真实使用记录，可按版本和硬件筛选
共 0 条

    还没有人点评。第一个说出真实体验的人最有价值。

    README 原文

    未翻译
    在 GitHub 打开

    Run 🤗 Transformers directly in your browser, with no need for a server!

    Transformers.js is designed to be functionally equivalent to Hugging Face's transformers python library, meaning you can run the same pretrained models using a very similar API. These models support common tasks in different modalities, such as:

    • 📝 Natural Language Processing: text classification, named entity recognition, question answering, language modeling, summarization, translation, multiple choice, and text generation.
    • 🖼️ Computer Vision: image classification, object detection, segmentation, and depth estimation.
    • 🗣️ Audio: automatic speech recognition, audio classification, and text-to-speech.
    • 🐙 Multimodal: embeddings, zero-shot audio classification, zero-shot image classification, and zero-shot object detection.

    Transformers.js uses ONNX Runtime to run models in the browser. The best part about it, is that you can easily convert your pretrained PyTorch, TensorFlow, or JAX models to ONNX using 🤗 Optimum.

    For more information, check out the full documentation.

    Installation

    To install via NPM, run:

    npm i @huggingface/transformers

    Alternatively, you can use it in vanilla JS, without any bundler, by using a CDN or static hosting. For example, using ES Modules, you can import the library with:

    <script type="module">
    import { pipeline } from 'https://cdn.jsdelivr.net/npm/@huggingface/[email protected]';
</script>

    Quick tour

    It's super simple to translate from existing code! Just like the python library, we support the pipeline API. Pipelines group together a pretrained model with preprocessing of inputs and postprocessing of outputs, making it the easiest way to run models with the library.

    from transformers import pipeline

# Allocate a pipeline for sentiment-analysis
pipe = pipeline('sentiment-analysis')

out = pipe('I love transformers!')
# [{'label': 'POSITIVE', 'score': 0.999806941}]

    import { pipeline } from '@huggingface/transformers';

// Allocate a pipeline for sentiment-analysis
const pipe = await pipeline('sentiment-analysis');

const out = await pipe('I love transformers!');
// [{'label': 'POSITIVE', 'score': 0.999817686}]

    You can also use a different model by specifying the model id or path as the second argument to the pipeline function. For example:

    // Use a different model for sentiment-analysis
const pipe = await pipeline('sentiment-analysis', 'Xenova/bert-base-multilingual-uncased-sentiment');

    By default, when running in the browser, the model will be run on your CPU (via WASM). If you would like to run the model on your GPU (via WebGPU), you can do this by setting device: 'webgpu', for example:

    // Run the model on WebGPU
const pipe = await pipeline('sentiment-analysis', 'Xenova/distilbert-base-uncased-finetuned-sst-2-english', {
  device: 'webgpu',
});

    For more information, check out the WebGPU guide.

    [!WARNING] The WebGPU API is still experimental in many browsers, so if you run into any issues, please file a bug report.

    In resource-constrained environments, such as web browsers, it is advisable to use a quantized version of the model to lower bandwidth and optimize performance. This can be achieved by adjusting the dtype option, which allows you to select the appropriate data type for your model. While the available options may vary depending on the specific model, typical choices include "fp32" (default for WebGPU), "fp16", "q8" (default for WASM), and "q4". For more information, check out the quantization guide.

    // Run the model at 4-bit quantization
const pipe = await pipeline('sentiment-analysis', 'Xenova/distilbert-base-uncased-finetuned-sst-2-english', {
  dtype: 'q4',
});

    Ready to dive in? Explore our wide variety of demo applications and templates here. You can also launch your own project instantly using the official Transformers.js template on Hugging Face!

    Custom usage

    By default, Transformers.js uses hosted pretrained models and precompiled WASM binaries, which should work out-of-the-box. You can customize this as follows:

    Settings

    import { env } from '@huggingface/transformers';

// Specify a custom location for models (defaults to '/models/').
env.localModelPath = '/path/to/models/';

// Disable the loading of remote models from the Hugging Face Hub:
env.allowRemoteModels = false;

// Set location of .wasm files. Defaults to use a CDN.
env.backends.onnx.wasm.wasmPaths = '/path/to/files/';

    For a full list of available settings, check out the API Reference.

    Convert your models to ONNX

    We recommend using Optimum to convert your PyTorch models to ONNX in a single command. For the full list of supported architectures, check out the Optimum documentation.

    Supported tasks/models

    Here is the list of all tasks and architectures currently supported by Transformers.js. If you don't see your task/model listed here or it is not yet supported, feel free to open a feature request here.

    To find compatible models on the Hub, select the "transformers.js" library tag in the filter menu (or visit this link). You can refine your search by selecting the task you're interested in (e.g., text-classification).

    Tasks

    Natural Language Processing
    TaskIDDescriptionSupported?
    Fill-Maskfill-maskMasking some of the words in a sentence and predicting which words should replace those masks.✅ (docs)(models)
    Question Answeringquestion-answeringRetrieve the answer to a question from a given text.✅ (docs)(models)
    Sentence Similaritysentence-similarityDetermining how similar two texts are.✅ (docs)(models)
    SummarizationsummarizationProducing a shorter version of a document while preserving its important information.✅ (docs)(models)
    Table Question Answeringtable-question-answeringAnswering a question about information from a given table.❌
    Text Classificationtext-classification or sentiment-analysisAssigning a label or class to a given text.✅ (docs)(models)
    Text Generationtext-generationProducing new text by predicting the next word in a sequence.✅ (docs)(models)
    Text-to-text Generationtext2text-generationConverting one text sequence into another text sequence.✅ (docs)(models)
    Token Classificationtoken-classification or nerAssigning a label to each token in a text.✅ (docs)(models)
    TranslationtranslationConverting text from one language to another.✅ (docs)(models)
    Zero-Shot Classificationzero-shot-classificationClassifying text into classes that are unseen during training.✅ (docs)(models)
    Feature Extractionfeature-extractionTransforming raw data into numerical features that can be processed while preserving the information in the original dataset.✅ (docs)(models)
    Vision
    TaskIDDescriptionSupported?
    Background Removalbackground-removalIsolating the main subject of an image by removing or making the background transparent.✅ (docs)(models)
    Depth Estimationdepth-estimationPredicting the depth of objects present in an image.✅ (docs)(models)
    Image Classificationimage-classificationAssigning a label or class to an entire image.✅ (docs)(models)
    Image Segmentationimage-segmentationDivides an image into segments where each pixel is mapped to an object. This task has multiple variants such as instance segmentation, panoptic segmentation and semantic segmentation.✅ (docs)(models)
    Image-to-Imageimage-to-imageTransforming a source image to match the characteristics of a target image or a target image domain.✅ (docs)(models)
    Mask Generationmask-generationGenerate masks for the objects in an image.❌
    Object Detectionobject-detectionIdentify objects of certain defined classes within an image.✅ (docs)(models)
    Video Classificationn/aAssigning a label or class to an entire video.❌
    Unconditional Image Generationn/aGenerating images with no condition in any context (like a prompt text or another image).❌
    Image Feature Extractionimage-feature-extractionTransforming raw data into numerical features that can be processed while preserving the information in the original image.✅ (docs)(models)
    Audio
    TaskIDDescriptionSupported?
    Audio Classificationaudio-classificationAssigning a label or class to a given audio.✅ (docs)(models)
    Audio-to-Audion/aGenerating audio from an input audio source.❌
    Automatic Speech Recognitionautomatic-speech-recognitionTranscribing a given audio into text.✅ (docs)(models)
    Text-to-Speechtext-to-speech or text-to-audioGenerating natural-sounding speech given text input.✅ (docs)(models)
    Tabular
    TaskIDDescriptionSupported?
    Tabular Classificationn/aClassifying a target category (a group) based on set of attributes.❌
    Tabular Regressionn/aPredicting a numerical value given a set of attributes.❌
    Multimodal
    TaskIDDescriptionSupported?
    Document Question Answeringdocument-question-answeringAnswering questions on document images.✅ (docs)(models)
    Image-to-Textimage-to-textOutput text from a given image.✅ (docs)(models)
    Text-to-Imagetext-to-imageGenerates images from input text.❌
    Visual Question Answeringvisual-question-answeringAnswering open-ended questions based on an image.❌
    Zero-Shot Audio Classificationzero-shot-audio-classificationClassifying audios into classes that are unseen during training.✅ (docs)(models)
    Zero-Shot Image Classificationzero-shot-image-classificationClassifying images into classes that are unseen during training.✅ (docs)(models)
    Zero-Shot Object Detectionzero-shot-object-detectionIdentify objects of classes that are unseen during training.✅ (docs)(models)
    Reinforcement Learning
    TaskIDDescriptionSupported?
    Reinforcement Learningn/aLearning from actions by interacting with an environment through trial and error and receiving rewards (negative or positive) as feedback.✅

    Models

    1. AFMoE (from Arcee AI, Prime Intellect, and DatologyAI) released with the paper Arcee Trinity Large Technical Report, by Varun Singh, Lucas Krauss, Sami Jaghouar, Matej Sirovatka, Charles Goddard, Fares Obied, Jack Min Ong, Jannik Straube, Fern, Aria Harley, Conner Stewart, Colin Kealty, Maziyar Panahi, Simon Kirsten, Anushka Deshpande, Anneketh Vij, Arthur Bresnu, Pranav Veldurthi, Raghav Ravishankar, Hardik Bishnoi, Mark McQuade, Johannes Hagemann, Lucas Atkins.
    2. ALBERT (from Google Research and the Toyota Technological Institute at Chicago) released with the paper ALBERT: A Lite BERT for Self-supervised Learning of Language Representations, by Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut.
    3. Arcee (from Arcee AI) released with the blog post Announcing Arcee Foundation Models by Fernando Fernandes, Varun Singh, Charles Goddard, Lucas Atkins, Mark McQuade, Maziyar Panahi, Conner Stewart, Colin Kealty, Raghav Ravishankar, Lucas Krauss, Anneketh Vij, Pranav Veldurthi, Abhishek Thakur, Julien Simon, Scott Zembsch, Benjamin Langer, Aleksiej Cecocho, Maitri Patel.
    4. Audio Spectrogram Transformer (from MIT) released with the paper AST: Audio Spectrogram Transformer by Yuan Gong, Yu-An Chung, James Glass.
    5. BART (from Facebook) released with the paper BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension by Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Ves Stoyanov and Luke Zettlemoyer.
    6. BEiT (from Microsoft) released with the paper BEiT: BERT Pre-Training of Image Transformers by Hangbo Bao, Li Dong, Furu Wei.
    7. BERT (from Google) released with the paper BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding by Jacob Devlin, Ming-Wei Chang, Kenton Lee and Kristina Toutanova.
    8. Blenderbot (from Facebook) released with the paper Recipes for building an open-domain chatbot by Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Kurt Shuster, Eric M. Smith, Y-Lan Boureau, Jason Weston.
    9. BlenderbotSmall (from Facebook) released with the paper Recipes for building an open-domain chatbot by Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Kurt Shuster, Eric M. Smith, Y-Lan Boureau, Jason Weston.
    10. BLOOM (from BigScience workshop) released by the BigScience Workshop.
    11. CamemBERT (from Inria/Facebook/Sorbonne) released with the paper CamemBERT: a Tasty French Language Model by Louis Martin*, Benjamin Muller*, Pedro Javier Ortiz Suárez*, Yoann Dupont, Laurent Romary, Éric Villemonte de la Clergerie, Djamé Seddah and Benoît Sagot.
    12. CHMv2 (from Meta) released with the paper CHMv2: Improvements in Global Canopy Height Mapping using DINOv3 by John Brandt, Seungeun Yi, Jamie Tolan, Xinyuan Li, Peter Potapov, Jessica Ertel, Justine Spore, Huy V. Vo, Michaël Ramamonjisoa, Patrick Labatut, Piotr Bojanowski, Camille Couprie.
    13. Chatterbox (from Resemble AI) released with the repository Chatterbox TTS by the Resemble AI team.
    14. Chinese-CLIP (from OFA-Sys) released with the paper Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese by An Yang, Junshu Pan, Junyang Lin, Rui Men, Yichang Zhang, Jingren Zhou, Chang Zhou.
    15. CLAP (from LAION-AI) released with the paper Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation by Yusong Wu, Ke Chen, Tianyu Zhang, Yuchen Hui, Taylor Berg-Kirkpatrick, Shlomo Dubnov.
    16. CLIP (from OpenAI) released with the paper Learning Transferable Visual Models From Natural Language Supervision by Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, Ilya Sutskever.
    17. CLIPSeg (from University of Göttingen) released with the paper Image Segmentation Using Text and Image Prompts by Timo Lüddecke and Alexander Ecker.
    18. CodeGen (from Salesforce) released with the paper A Conversational Paradigm for Program Synthesis by Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, Caiming Xiong.
    19. CodeLlama (from MetaAI) released with the paper Code Llama: Open Foundation Models for Code by Baptiste Rozière, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Tal Remez, Jérémy Rapin, Artyom Kozhevnikov, Ivan Evtimov, Joanna Bitton, Manish Bhatt, Cristian Canton Ferrer, Aaron Grattafiori, Wenhan Xiong, Alexandre Défossez, Jade Copet, Faisal Azhar, Hugo Touvron, Louis Martin, Nicolas Usunier, Thomas Scialom, Gabriel Synnaeve.
    20. Cohere (from Cohere) released with the blog post Command-R: Retrieval Augmented Generation at Production Scale by Cohere.
    21. Cohere2 (from Cohere) released with the blog post Introducing Command R7B: Fast and efficient generative AI by Cohere.
    22. Cohere ASR (from Cohere) released with the blog post Introducing Cohere Transcribe: a new state-of-the-art in open-source speech recognition by Cohere.
    23. ConvBERT (from YituTech) released with the paper ConvBERT: Improving BERT with Span-based Dynamic Convolution by Zihang Jiang, Weihao Yu, Daquan Zhou, Yunpeng Chen, Jiashi Feng, Shuicheng Yan.
    24. ConvNeXT (from Facebook AI) released with the paper A ConvNet for the 2020s by Zhuang Liu, Hanzi Mao, Chao-Yuan Wu, Christoph Feichtenhofer, Trevor Darrell, Saining Xie.
    25. ConvNeXTV2 (from Facebook AI) released with the paper ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders by Sanghyun Woo, Shoubhik Debnath, Ronghang Hu, Xinlei Chen, Zhuang Liu, In So Kweon, Saining Xie.
    26. D-FINE (from University of Science and Technology of China) released with the paper D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement by Yansong Peng, Hebei Li, Peixi Wu, Yueyi Zhang, Xiaoyan Sun, Feng Wu.
    27. DAC (from Descript) released with the paper Descript Audio Codec: High-Fidelity Audio Compression with Improved RVQGAN by Rithesh Kumar, Prem Seetharaman, Alejandro Luebs, Ishaan Kumar, Kundan Kumar.
    28. DeBERTa (from Microsoft) released with the paper DeBERTa: Decoding-enhanced BERT with Disentangled Attention by Pengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu Chen.
    29. DeBERTa-v2 (from Microsoft) released with the paper DeBERTa: Decoding-enhanced BERT with Disentangled Attention by Pengcheng He, Xiaodong Liu, Jianfeng Gao, Weizhu Chen.
    30. Decision Transformer (from Berkeley/Facebook/Google) released with the paper Decision Transformer: Reinforcement Learning via Sequence Modeling by Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas, Igor Mordatch.
    31. DeepSeek-V3 (from DeepSeek-AI) released with the paper DeepSeek-V3 Technical Report by the DeepSeek-AI team.
    32. DeepSeek-V4 (from DeepSeek-AI) released with the paper DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence by the DeepSeek-AI team.
    33. DeiT (from Facebook) released with the paper Training data-efficient image transformers & distillation through attention by Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, Hervé Jégou.
    34. Depth Anything (from University of Hong Kong and TikTok) released with the paper Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data by Lihe Yang, Bingyi Kang, Zilong Huang, Xiaogang Xu, Jiashi Feng, Hengshuang Zhao.
    35. Depth Pro (from Apple) released with the paper Depth Pro: Sharp Monocular Metric Depth in Less Than a Second by Aleksei Bochkovskii, Amaël Delaunoy, Hugo Germain, Marcel Santos, Yichao Zhou, Stephan R. Richter, Vladlen Koltun.
    36. DETR (from Facebook) released with the paper End-to-End Object Detection with Transformers by Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, Sergey Zagoruyko.
    37. DINOv2 (from Meta AI) released with the paper DINOv2: Learning Robust Visual Features without Supervision by Maxime Oquab, Timothée Darcet, Théo Moutakanni, Huy Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El-Nouby, Mahmoud Assran, Nicolas Ballas, Wojciech Galuba, Russell Howes, Po-Yao Huang, Shang-Wen Li, Ishan Misra, Michael Rabbat, Vasu Sharma, Gabriel Synnaeve, Hu Xu, Hervé Jegou, Julien Mairal, Patrick Labatut, Armand Joulin, Piotr Bojanowski.
    38. DINOv2 with Registers (from Meta AI) released with the paper DINOv2 with Registers by Timothée Darcet, Maxime Oquab, Julien Mairal, Piotr Bojanowski.
    39. DINOv3 (from Meta AI) released with the paper DINOv3 by Oriane Siméoni, Huy V. Vo, Maximilian Seitzer, Federico Baldassarre, Maxime Oquab, Cijo Jose, Vasil Khalidov, Marc Szafraniec, Seungeun Yi, Michaël Ramamonjisoa, Francisco Massa, Daniel Haziza, Luca Wehrstedt, Jianyuan Wang, Timothée Darcet, Théo Moutakanni, Leonel Sentana, Claire Roberts, Andrea Vedaldi, Jamie Tolan, John Brandt, Camille Couprie, Julien Mairal, Hervé Jégou, Patrick Labatut, Piotr Bojanowski.
    40. DistilBERT (from HuggingFace), released together with the paper DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter by Victor Sanh, Lysandre Debut and Thomas Wolf. The same method has been applied to compress GPT2 into DistilGPT2, RoBERTa into DistilRoBERTa, Multilingual BERT into DistilmBERT and a German version of DistilBERT.
    41. DiT (from Microsoft Research) released with the paper DiT: Self-supervised Pre-training for Document Image Transformer by Junlong Li, Yiheng Xu, Tengchao Lv, Lei Cui, Cha Zhang, Furu Wei.
    42. Donut (from NAVER), released together with the paper OCR-free Document Understanding Transformer by Geewook Kim, Teakgyu Hong, Moonbin Yim, Jeongyeon Nam, Jinyoung Park, Jinyeong Yim, Wonseok Hwang, Sangdoo Yun, Dongyoon Han, Seunghyun Park.
    43. DPT (from Intel Labs) released with the paper Vision Transformers for Dense Prediction by René Ranftl, Alexey Bochkovskiy, Vladlen Koltun.
    44. EdgeTAM (from Facebook) released with the paper EdgeTAM: On-Device Track Anything Model by Chong Zhou, Chenchen Zhu, Yunyang Xiong, Saksham Suri, Fanyi Xiao, Lemeng Wu, Raghuraman Krishnamoorthi, Bo Dai, Chen Change Loy, Vikas Chandra, Bilge Soran.
    45. EfficientNet (from Google Brain) released with the paper EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks by Mingxing Tan, Quoc V. Le.
    46. ELECTRA (from Google Research/Stanford University) released with the paper ELECTRA: Pre-training text encoders as discriminators rather than generators by Kevin Clark, Minh-Thang Luong, Quoc V. Le, Christopher D. Manning.
    47. ERNIE-4.5 (from Baidu ERNIE Team) released with the blog post Announcing the Open Source Release of the ERNIE 4.5 Model Family by the Baidu ERNIE Team.
    48. ESM (from Meta AI) are transformer protein language models. ESM-1b was released with the paper Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences by Alexander Rives, Joshua Meier, Tom Sercu, Siddharth Goyal, Zeming Lin, Jason Liu, Demi Guo, Myle Ott, C. Lawrence Zitnick, Jerry Ma, and Rob Fergus. ESM-1v was released with the paper Language models enable zero-shot prediction of the effects of mutations on protein function by Joshua Meier, Roshan Rao, Robert Verkuil, Jason Liu, Tom Sercu and Alexander Rives. ESM-2 and ESMFold were released with the paper Language models of protein sequences at the scale of evolution enable accurate structure prediction by Zeming Lin, Halil Akin, Roshan Rao, Brian Hie, Zhongkai Zhu, Wenting Lu, Allan dos Santos Costa, Maryam Fazel-Zarandi, Tom Sercu, Sal Candido, Alexander Rives.
    49. EuroBERT (from the EuroBERT team) released with the paper EuroBERT: Scaling Multilingual Encoders for European Languages by Nicolas Boizard, Hippolyte Gisserot-Boukhlef, Duarte M. Alves, André Martins, Ayoub Hammal, Caio Corro, Céline Hudelot, Emmanuel Malherbe, Etienne Malaboeuf, Fanny Jourdan, Gabriel Hautreux, João Alves, Kevin El-Haddad, Manuel Faysse, Maxime Peyrard, Nuno M. Guerreiro, Patrick Fernandes, Ricardo Rei, Pierre Colombo.
    50. EXAONE (from LG AI Research) released with the papers EXAONE 3.0 7.8B Instruction Tuned Language Model and EXAONE 3.5: Series of Large Language Models for Real-world Use Cases by the LG AI Research team.
    51. Falcon (from Technology Innovation Institute) by Almazrouei, Ebtesam and Alobeidli, Hamza and Alshamsi, Abdulaziz and Cappelli, Alessandro and Cojocaru, Ruxandra and Debbah, Merouane and Goffinet, Etienne and Heslow, Daniel and Launay, Julien and Malartic, Quentin and Noune, Badreddine and Pannier, Baptiste and Penedo, Guilherme.
    52. FalconH1 (from Technology Innovation Institute) released with the blog post Falcon-H1-Tiny: A series of extremely small, yet powerful language models redefining capabilities at small scale by the Falcon-LLM team.
    53. FastViT (from Apple) released with the paper FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization by Pavan Kumar Anasosalu Vasu, James Gabriel, Jeff Zhu, Oncel Tuzel and Anurag Ranjan.
    54. FLAN-T5 (from Google AI) released in the repository google-research/t5x by Hyung Won Chung, Le Hou, Shayne Longpre, Barret Zoph, Yi Tay, William Fedus, Eric Li, Xuezhi Wang, Mostafa Dehghani, Siddhartha Brahma, Albert Webson, Shixiang Shane Gu, Zhuyun Dai, Mirac Suzgun, Xinyun Chen, Aakanksha Chowdhery, Sharan Narang, Gaurav Mishra, Adams Yu, Vincent Zhao, Yanping Huang, Andrew Dai, Hongkun Yu, Slav Petrov, Ed H. Chi, Jeff Dean, Jacob Devlin, Adam Roberts, Denny Zhou, Quoc V. Le, and Jason Wei
    55. Florence2 (from Microsoft) released with the paper Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks by Bin Xiao, Haiping Wu, Weijian Xu, Xiyang Dai, Houdong Hu, Yumao Lu, Michael Zeng, Ce Liu, Lu Yuan.
    56. Gemma (from Google) released with the blog post Gemma: Open Models Based on Gemini Technology and Research by the Gemma Google team.
    57. Gemma2 (from Google) released with the blog post Gemma2: Open Models Based on Gemini Technology and Research by the Gemma Google team.
    58. Gemma3 (from Google) released with the blog post Introducing Gemma 3: The most capable model you can run on a single GPU or TPU by the Gemma Google team.
    59. Gemma3n (from Google) released with the blog post Announcing Gemma 3n preview: powerful, efficient, mobile-first AI by the Gemma Google team.
    60. Gemma4 (from Google) released with the blog post Gemma 4 by the Gemma Google team.
    61. GLM (from the GLM Team, THUDM & ZhipuAI) released with the paper ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools by Team GLM: Aohan Zeng, Bin Xu, Bowen Wang, Chenhui Zhang, Da Yin, Dan Zhang, Diego Rojas, Guanyu Feng, Hanlin Zhao, Hanyu Lai, Hao Yu, Hongning Wang, Jiadai Sun, Jiajie Zhang, Jiale Cheng, Jiayi Gui, Jie Tang, Jing Zhang, Jingyu Sun, Juanzi Li, Lei Zhao, Lindong Wu, Lucen Zhong, Mingdao Liu, Minlie Huang, Peng Zhang, Qinkai Zheng, Rui Lu, Shuaiqi Duan, Shudan Zhang, Shulin Cao, Shuxun Yang, Weng Lam Tam, Wenyi Zhao, Xiao Liu, Xiao Xia, Xiaohan Zhang, Xiaotao Gu, Xin Lv, Xinghan Liu, Xinyi Liu, Xinyue Yang, Xixuan Song, Xunkai Zhang, Yifan An, Yifan Xu, Yilin Niu, Yuantao Yang, Yueyan Li, Yushi Bai, Yuxiao Dong, Zehan Qi, Zhaoyu Wang, Zhen Yang, Zhengxiao Du, Zhenyu Hou, Zihan Wang.
    62. GLM-MoE-DSA (from the GLM Team, ZhipuAI & Tsinghua University) released with the paper GLM-5: from Vibe Coding to Agentic Engineering by Team GLM.
    63. GLM-OCR (from the GLM Team, ZhipuAI & Tsinghua University) released with the paper GLM-OCR Technical Report by Team GLM: Shuaiqi Duan, Yadong Xue, Weihan Wang, Zhe Su, Huan Liu, Sheng Yang, Guobing Gan, Guo Wang, Zihan Wang, Shengdong Yan, Dexin Jin, Yuxuan Zhang, Guohong Wen, Yanfeng Wang, Yutao Zhang, Xiaohan Zhang, Wenyi Hong, Yukuo Cen, Da Yin, Bin Chen, Wenmeng Yu, Xiaotao Gu, Jie Tang.
    64. GLPN (from KAIST) released with the paper Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth by Doyeon Kim, Woonghyun Ga, Pyungwhan Ahn, Donggyu Joo, Sehwan Chun, Junmo Kim.
    65. GPT Neo (from EleutherAI) released in the repository EleutherAI/gpt-neo by Sid Black, Stella Biderman, Leo Gao, Phil Wang and Connor Leahy.
    66. GPT NeoX (from EleutherAI) released with the paper GPT-NeoX-20B: An Open-Source Autoregressive Language Model by Sid Black, Stella Biderman, Eric Hallahan, Quentin Anthony, Leo Gao, Laurence Golding, Horace He, Connor Leahy, Kyle McDonell, Jason Phang, Michael Pieler, USVSN Sai Prashanth, Shivanshu Purohit, Laria Reynolds, Jonathan Tow, Ben Wang, Samuel Weinbach
    67. GPT OSS (from OpenAI) released with the blog Introducing gpt-oss by Sandhini Agarwal, Lama Ahmad, Jason Ai, Sam Altman, Andy Applebaum, Edwin Arbus, Rahul K. Arora, Yu Bai, Bowen Baker, Haiming Bao, Boaz Barak, Ally Bennett, Tyler Bertao, Nivedita Brett, Eugene Brevdo, Greg Brockman, Sebastien Bubeck, Che Chang, Kai Chen, Mark Chen, Enoch Cheung, Aidan Clark, Dan Cook, Marat Dukhan, Casey Dvorak, Kevin Fives, Vlad Fomenko, Timur Garipov, Kristian Georgiev, Mia Glaese, Tarun Gogineni, Adam Goucher, Lukas Gross, Katia Gil Guzman, John Hallman, Jackie Hehir, Johannes Heidecke, Alec Helyar, Haitang Hu, Romain Huet, Jacob Huh, Saachi Jain, Zach Johnson, Chris Koch, Irina Kofman, Dominik Kundel, Jason Kwon, Volodymyr Kyrylov, Elaine Ya Le, Guillaume Leclerc, James Park Lennon, Scott Lessans, Mario Lezcano-Casado, Yuanzhi Li, Zhuohan Li, Ji Lin, Jordan Liss, Lily (Xiaoxuan) Liu, Jiancheng Liu, Kevin Lu, Chris Lu, Zoran Martinovic, Lindsay McCallum, Josh McGrath, Scott McKinney, Aidan McLaughlin, Song Mei, Steve Mostovoy, Tong Mu, Gideon Myles, Alexander Neitz, Alex Nichol, Jakub Pachocki, Alex Paino, Dana Palmie, Ashley Pantuliano, Giambattista Parascandolo, Jongsoo Park, Leher Pathak, Carolina Paz, Ludovic Peran, Dmitry Pimenov, Michelle Pokrass, Elizabeth Proehl, Huida Qiu, Gaby Raila, Filippo Raso, Hongyu Ren, Kimmy Richardson, David Robinson, Bob Rotsted, Hadi Salman, Suvansh Sanjeev, Max Schwarzer, D. Sculley, Harshit Sikchi, Kendal Simon, Karan Singhal, Yang Song, Dane Stuckey, Zhiqing Sun, Philippe Tillet, Sam Toizer, Foivos Tsimpourlas, Nikhil Vyas, Eric Wallace, Xin Wang, Miles Wang, Olivia Watkins, Kevin Weil, Amy Wendling, Kevin Whinnery, Cedric Whitney, Hannah Wong, Lin Yang, Yu Yang, Michihiro Yasunaga, Kristen Ying, Wojciech Zaremba, Wenting Zhan, Cyril Zhang, Brian Zhang, Eddie Zhang, Shengjia Zhao.
    68. GPT-2 (from OpenAI) released with the paper Language Models are Unsupervised Multitask Learners by Alec Radford*, Jeffrey Wu*, Rewon Child, David Luan, Dario Amodei** and Ilya Sutskever**.
    69. GPT-J (from EleutherAI) released in the repository kingoflolz/mesh-transformer-jax by Ben Wang and Aran Komatsuzaki.
    70. GPTBigCode (from BigCode) released with the paper SantaCoder: don't reach for the stars! by Loubna Ben Allal, Raymond Li, Denis Kocetkov, Chenghao Mou, Christopher Akiki, Carlos Munoz Ferrandis, Niklas Muennighoff, Mayank Mishra, Alex Gu, Manan Dey, Logesh Kumar Umapathi, Carolyn Jane Anderson, Yangtian Zi, Joel Lamy Poirier, Hailey Schoelkopf, Sergey Troshin, Dmitry Abulkhanov, Manuel Romero, Michael Lappert, Francesco De Toni, Bernardo García del Río, Qian Liu, Shamik Bose, Urvashi Bhattacharyya, Terry Yue Zhuo, Ian Yu, Paulo Villegas, Marco Zocca, Sourab Mangrulkar, David Lansky, Huu Nguyen, Danish Contractor, Luis Villa, Jia Li, Dzmitry Bahdanau, Yacine Jernite, Sean Hughes, Daniel Fried, Arjun Guha, Harm de Vries, Leandro von Werra.
    71. Granite (from IBM) released with the paper Power Scheduler: A Batch Size and Token Number Agnostic Learning Rate Scheduler by Yikang Shen, Matthew Stallone, Mayank Mishra, Gaoyuan Zhang, Shawn Tan, Aditya Prasad, Adriana Meza Soria, David D. Cox, Rameswar Panda.
    72. GraniteMoeHybrid (from IBM) released with the blog post IBM Granite 4.0: hyper-efficient, high performance hybrid models for enterprise by the IBM Granite team.
    73. Granite Speech (from IBM) released with the paper Granite-speech: open-source speech-aware LLMs with strong English ASR capabilities by the IBM Granite team.
    74. Grounding DINO (from IDEA-Research) released with the paper Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection by Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Qing Jiang, Chunyuan Li, Jianwei Yang, Hang Su, Jun Zhu, Lei Zhang.
    75. GroupViT (from UCSD, NVIDIA) released with the paper GroupViT: Semantic Segmentation Emerges from Text Supervision by Jiarui Xu, Shalini De Mello, Sifei Liu, Wonmin Byeon, Thomas Breuel, Jan Kautz, Xiaolong Wang.
    76. Helium (from the Kyutai Team) released with the blog post Announcing Helium-1 Preview by the Kyutai Team.
    77. HerBERT (from Allegro.pl, AGH University of Science and Technology) released with the paper KLEJ: Comprehensive Benchmark for Polish Language Understanding by Piotr Rybak, Robert Mroczkowski, Janusz Tracz, Ireneusz Gawlik.
    78. HRM-Text (from Sapient Intelligence) released with the paper Hierarchical Reasoning Model by Guan Wang, Jin Li, Yuhao Sun, Xing Chen, Changling Liu, Yue Wu, Meng Lu, Sen Song, Yasin Abbasi Yadkori.
    79. Hiera (from Meta) released with the paper Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles by Chaitanya Ryali, Yuan-Ting Hu, Daniel Bolya, Chen Wei, Haoqi Fan, Po-Yao Huang, Vaibhav Aggarwal, Arkabandhu Chowdhury, Omid Poursaeed, Judy Hoffman, Jitendra Malik, Yanghao Li, Christoph Feichtenhofer.
    80. Hubert (from Facebook) released with the paper HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units by Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai, Kushal Lakhotia, Ruslan Salakhutdinov, Abdelrahman Mohamed.
    81. HunYuanDenseV1 (from Tencent) released with the paper Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent by the Tencent team.
    82. I-JEPA (from Meta) released with the paper Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture by Mahmoud Assran, Quentin Duval, Ishan Misra, Piotr Bojanowski, Pascal Vincent, Michael Rabbat, Yann LeCun, Nicolas Ballas.
    83. Idefics3 (from Hugging Face) released with the paper Building and better understanding vision-language models: insights and future directions by Hugo Laurençon, Andrés Marafioti, Victor Sanh, Léo Tronchon.
    84. JAIS (from Core42) released with the paper Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models by Neha Sengupta, Sunil Kumar Sahu, Bokang Jia, Satheesh Katipomu, Haonan Li, Fajri Koto, William Marshall, Gurpreet Gosal, Cynthia Liu, Zhiming Chen, Osama Mohammed Afzal, Samta Kamboj, Onkar Pandit, Rahul Pal, Lalit Pradhan, Zain Muhammad Mujahid, Massa Baali, Xudong Han, Sondos Mahmoud Bsharat, Alham Fikri Aji, Zhiqiang Shen, Zhengzhong Liu, Natalia Vassilieva, Joel Hestness, Andy Hock, Andrew Feldman, Jonathan Lee, Andrew Jackson, Hector Xuguang Ren, Preslav Nakov, Timothy Baldwin, Eric Xing.
    85. Janus (from DeepSeek) released with the paper Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation Chengyue Wu, Xiaokang Chen, Zhiyu Wu, Yiyang Ma, Xingchao Liu, Zizheng Pan, Wen Liu, Zhenda Xie, Xingkai Yu, Chong Ruan, Ping Luo.
    86. JinaCLIP (from Jina AI) released with the paper Jina CLIP: Your CLIP Model Is Also Your Text Retriever by Andreas Koukounas, Georgios Mastrapas, Michael Günther, Bo Wang, Scott Martens, Isabelle Mohr, Saba Sturua, Mohammad Kalim Akram, Joan Fontanals Martínez, Saahil Ognawala, Susana Guzman, Maximilian Werk, Nan Wang, Han Xiao.
    87. LiteWhisper (from University of Washington, Kotoba Technologies) released with the paper LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximation by Keisuke Kamahori, Jungo Kasai, Noriyuki Kojima, Baris Kasikci.
    88. LongT5 (from Google AI) released with the paper LongT5: Efficient Text-To-Text Transformer for Long Sequences by Mandy Guo, Joshua Ainslie, David Uthus, Santiago Ontanon, Jianmo Ni, Yun-Hsuan Sung, Yinfei Yang.
    89. LFM2 (from Liquid AI) released with the blog post Introducing LFM2: The Fastest On-Device Foundation Models on the Market by the Liquid AI Team.
    90. Lfm2Moe (from Liquid AI) released with the blog post LFM2-8B-A1B: An Efficient On-device Mixture-of-Experts by the Liquid AI Team.
    91. LFM2-VL (from Liquid AI) released with the blog post LFM2-VL: Efficient Vision-Language Models by the Liquid AI Team.
    92. LFM3 (from Liquid AI) released with the blog post Introducing LFM3: Every Modality for Specialized Intelligence by the Liquid AI Team.
    93. LFM3-VL (from Liquid AI) released with the blog post Introducing LFM3: Every Modality for Specialized Intelligence by the Liquid AI Team.
    94. LightOnOcr (from LightOn) released with the blog post LightOnOCR-1B: The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR by the LightOn Team.
    95. LLaMA (from The FAIR team of Meta AI) released with the paper LLaMA: Open and Efficient Foundation Language Models by Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, Guillaume Lample.
    96. Llama2 (from The FAIR team of Meta AI) released with the paper Llama2: Open Foundation and Fine-Tuned Chat Models by Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, Dan Bikel, Lukas Blecher, Cristian Canton Ferrer, Moya Chen, Guillem Cucurull, David Esiobu, Jude Fernandes, Jeremy Fu, Wenyin Fu, Brian Fuller, Cynthia Gao, Vedanuj Goswami, Naman Goyal, Anthony Hartshorn, Saghar Hosseini, Rui Hou, Hakan Inan, Marcin Kardas, Viktor Kerkez Madian Khabsa, Isabel Kloumann, Artem Korenev, Punit Singh Koura, Marie-Anne Lachaux, Thibaut Lavril, Jenya Lee, Diana Liskovich, Yinghai Lu, Yuning Mao, Xavier Martinet, Todor Mihaylov, Pushka rMishra, Igor Molybog, Yixin Nie, Andrew Poulton, Jeremy Reizenstein, Rashi Rungta, Kalyan Saladi, Alan Schelten, Ruan Silva, Eric Michael Smith, Ranjan Subramanian, Xiaoqing EllenTan, Binh Tang, Ross Taylor, Adina Williams, Jian Xiang Kuan, Puxin Xu, Zheng Yan, Iliyan Zarov, Yuchen Zhang, Angela Fan, Melanie Kambadur, Sharan Narang, Aurelien Rodriguez, Robert Stojnic, Sergey Edunov, Thomas Scialom.
    97. Llama3 (from The FAIR team of Meta AI) released with the paper The Llama 3 Herd of Models by the Llama Team at Meta.
    98. Llama4 (from The FAIR team of Meta AI) released with the blog post The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation by the Llama Team at Meta.
    99. LLaVa (from Microsoft Research & University of Wisconsin-Madison) released with the paper Visual Instruction Tuning by Haotian Liu, Chunyuan Li, Yuheng Li and Yong Jae Lee.
    100. LLaVA-OneVision (from ByteDance & NTU & CUHK & HKUST) released with the paper LLaVA-OneVision: Easy Visual Task Transfer by Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Yanwei Li, Ziwei Liu, Chunyuan Li
    101. M2M100 (from Facebook) released with the paper [Beyond English-Centric Multilingual Machine Translation](https://huggingface.co/papers/2010.111

    相关项目

    同分类里 star 最高的项目
    对比全部 →
    ollama
    ollama·Go

    本地一键跑起 Kimi、DeepSeek、Qwen、Gemma 等大模型，省去环境配置和依赖折腾，适合快速做推理和原型验证。

    本地推理+3大模型推理服务入门
    186472+28219kv0.40.152026-11-10 01:49 UTC
    llama.cpp
    ggml-org·C++

    用 C/C++ 实现的大模型推理引擎，能在普通 CPU 和消费级显卡上跑 LLaMA 等模型，支持量化以降低显存占用。

    推理引擎+4大模型推理服务入门
    133865+26825kb122332026-11-10 01:44 UTC
    vllm
    vllm-project·Python

    面向大语言模型的高吞吐、低显存推理与服务引擎，通过 PagedAttention 等优化显著提升并发吞吐并降低显存占用，适合部署在线推理服务。

    推理引擎+4大模型推理服务进阶
    96643+15025kv0.33.0rc32026-11-10 05:17 UTC
    jan
    janhq·Rust

    在本地电脑上离线运行大模型的桌面客户端，是 ChatGPT 的开源替代品，无需联网即可对话，数据不出本机。

    本地推理+4大模型推理服务
    45644+1023.2kv0.8.82026-11-10 04:20 UTC