transformers

Transformers 库快速入门教程

Python bindings for the Transformer models implemented in C/C++ using GGML library.

Practical course about Large Language Models.

Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ.

自然语言处理、知识图谱、对话系统，大模型等技术研究与应用。

maximal update parametrization (µP)

Implementation of Alphafold 3 from Google Deepmind in Pytorch

A compilation of the best multi-agent papers

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting

A SOTA quantization toolkit for high-accuracy low-bit LLM inference|简洁且高效的量化工具包

[PAMI'23] TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving; [CVPR'21] Multi-Modal Fusion Transformer for End-to-End Autonomous Driving

[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

Unified Training of Universal Time Series Forecasting Transformers

Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch

MLeap: Deploy ML Pipelines to Production

The data scientist's open-source choice to scale, assess and maintain natural language data. Treat training data like a software artifact.

A curriculum for learning about foundation models, from scratch to the frontier

Interface for OuteTTS models.

Korean BERT pre-trained cased (KoBERT)

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.

Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI

Scalable and memory-optimized training of diffusion models

An elegent pytorch implement of transformers

Curated visual catalog of 155+ vision-language model (VLM/MLLM) architectures: papers, diagrams, training recipes, datasets, and a release timeline for multimodal AI agents.

Jlama is a modern LLM inference engine for Java

A collection of resources on applications of Transformers in Medical Imaging.

Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.

LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.