🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
- nlp
- natural-language-processing
- pytorch
- pytorch-transformers
107,098 visible repositories in the index
1–24 of 522 · Most stars
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
Port of OpenAI's Whisper model in C/C++
Training-free language model modification: Remove censorship, suppress slop, reduce sycophancy, and more
SGLang is a high-performance serving framework for large language models and multimodal models.
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
SOTA Open Source TTS
OpenMMLab Detection Toolbox and Benchmark
Faster Whisper transcription with CTranslate2
Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
[ECCV 2026 Best Paper Award Candidate] LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction
Ongoing research training transformer models at scale
[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
Datasets, Transforms and Models specific to Computer Vision
pix2tex: Using a ViT to convert images of equations into LaTeX code.
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.
Nano vLLM
State-of-the-art Machine Learning for the web. Run 🤗 Transformers directly in your browser, with no need for a server!
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM5.3, Gemma4, Llava, Phi4, ...) (AAAI 2025).
TranslatedA concise and elegant Dictionary and Translator macOS App for looking up words and translating text. Works out of the box, supports offline OCR recognition, and supports Youdao Dictionary, 🍎 Apple System Dictionary, 🍎 Apple System Translation, OpenAI, Gemini, DeepL, Google, Bing, Tencent, Baidu, Alibaba, Niutrans (小牛), Caiyun, and Volcano Translate.
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.