This repository contains the code and data for the paper "SelfIE: Self-Interpretation of Large Language Model Embeddings" by Haozhe Chen, Carl Vondrick, and Chengzhi Mao.

A series of math-specific large language models of our Qwen2 series.

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

PyTorch-native post-training at scale

An interface library for RL post training with environments.

The best ChatGPT that $100 can buy.

Video generation via code

Enabling Efficient Reasoning in LLMs via Black-box Adversarial Prompting

starVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

Fast Semantic Text Deduplication & Filtering

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Go ahead and axolotl questions

本仓库包含对 Claude Code v1.0.33 进行逆向工程的完整研究和分析资料。包括对混淆源代码的深度技术分析、系统架构文档，以及重构 Claude Code agent 系统的实现蓝图。主要发现包括实时 Steering 机制、多 Agent 架构、智能上下文管理和工具执行管道。该项目为理解现代 AI agent 系统设计和实现提供技术参考。

Port of OpenAI's Whisper model in C/C++

PaCMAP: Large-scale Dimension Reduction Technique Preserving Both Global and Local Structure

MineContext is your proactive context-aware AI partner（Context-Engineering+ChatGPT Pulse）

A command-line interface tool for serving LLM using vLLM.

A curated list of resources on Reinforcement Learning with Verifiable Rewards (RLVR) and the reasoning capability boundary of Large Language Models (LLMs).

Training API

A Unified Framework for High-Performance and Extensible LLM Steering

Fully Open Framework for Democratized Multimodal Training

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors

Lightweight coding agent that runs in your terminal

Stanford NLP Python library for benchmarking the utility of LLM interpretability methods