“transformer”

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models

GPU-optimized library for training transformer models at scale

Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction

Less Code, Lower Barrier, Faster Deployment

Chronos: Pretrained Models for Time Series Forecasting

Fully automatic censorship removal for language models

A high-performance observability data pipeline

Train transformer language models with reinforcement learning.

A method for training a Large Language Model (LLM) from scratch using Python.

End-to-end framework for building custom AI applications and agents.

Implement a ChatGPT-like LLM in PyTorch from scratch

A high-throughput and memory-efficient inference and serving engine for LLMs

PaddleOCR: A powerful OCR toolkit for transforming PDFs/images into structured data

AI coding assistant skill that transforms various file types into a queryable knowledge graph

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs

Curriculum for building AI systems from scratch

SGLang high-performance serving framework

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications.

Machine Learning Engineering Open Book

Private AI platform for agents, assistants and enterprise search

Convert documents to structured data effortlessly

All-in-one AI framework for semantic search, LLM orchestration and language model workflows

Large Language Model Text Generation Inference

Run LLMs at home, BitTorrent-style

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray

Advancing open-source language models with imperfect data

Learn prompt engineering and generative AI with our free resources, courses, and on-demand webinars.

Task-based NLP engine for structured outputs from LLMs

AIGC/LLM/AI Agent算法岗面试求职秘籍

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

The Security Toolkit for LLM Interactions

Community maintained hardware plugin for vLLM on Ascend

Artificial Intelligence Controller Interface (AICI)

Practical course about Large Language Models

Prompt. Generate Synthetic Data. Train & Align Models.

API for searching, scraping, and interacting with the web at scale

A curated collection of AI agent projects and use cases

📚 从零开始构建大模型

Claude Code Game Studios turns a single Claude Code session into a full game development studio with 49 AI agents and 72 workflow skills.

RAG on Everything with LEANN