Single File, Single GPU, From Scratch, Efficient, Full Parameter Tuning library for "RL for LLMs"

A lightweight monitoring tool that leverages OS-level strace alongside Python audit hooks to detect sensitive operations during ML model execution.

Keep searching, reading webpages, reasoning until it finds the answer (or exceeding the token budget)

A high-performance distributed file system designed to address the challenges of AI training and inference workloads.

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

FlashMLA: Efficient Multi-head Latent Attention Kernels

“连续八年成为全世界最受喜爱的语言，无 GC 也无需手动内存管理、极高的性能和安全性、过程/OO/函数式编程、优秀的包管理、JS 未来基石" — 工作之余的第二语言来试试 Rust 吧。本书拥有全面且深入的讲解、生动贴切的示例、德芙般丝滑的内容，这可能是目前最用心的 Rust 中文学习教程 / Book

A technical explainer by @kognise of how your computer runs programs, from start to finish.

Djinn-Agent: A lightweight CLI tool for seamless interaction with Claude's advanced computer-use capabilities, automating complex tasks from the terminal.

Resources for the "Evaluating the Factual Consistency of Abstractive Text Summarization" paper

Master programming by recreating your favorite technologies from scratch.

Visualization and debugging tool for LangChain workflows

Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models

A curated list of Large Language Model (LLM) Interpretability resources.

经济学人(含音频)、纽约客、卫报、连线、大西洋月刊等英语杂志免费下载,支持epub、mobi、pdf格式, 每周更新

The automated prompt injection framework for LLM-integrated applications.

Resource, Evaluation and Detection Papers for ChatGPT

📋 A list of open LLMs available for commercial use.

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

Interact with your documents using the power of GPT, 100% privately, no data leaks

Generate 3D objects conditioned on text or images

Home of StarCoder: fine-tuning & inference!

Chinese-LLaMA 1&2、Chinese-Falcon 基础模型；ChatFlow中文对话模型；中文OpenLLaMA模型；NLP预训练/指令微调数据集

Panda项目是于2023年5月启动的开源海外中文大语言模型项目，致力于大模型时代探索整个技术栈，旨在推动中文自然语言处理领域的创新和合作。

Codebase for the ACL 2023 paper: White-Box Multi-Objective Adversarial Attack on Dialogue Generation.

🔊 Text-Prompted Generative Audio Model

[NeurIPS 22] [AAAI 24] Recurrent Transformer-based long-context architecture.

The official gpt4free repository | various collection of powerful language models | o4, o3 and deepseek r1, gpt-4.1, gemini 2.5