Code and data for "Lost in the Middle: How Language Models Use Long Contexts"

The official Github repository for paper "R^2AG: Incorporating Retrieval Information into Retrieval Augmented Generation".

YOLOv10: Real-Time End-to-End Object Detection

Source code and demo for memory bank and SiliconFriend

The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

Reverse engineered ChatGPT API

一些关于写论文的教程,防止犯一些低级错误

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

An Evolving Code Generation Benchmark Aligned with Real-world Code Repositories

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

本项目旨在分享大模型相关技术原理以及实战经验。

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版

A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

A large-scale, fine-grained, diverse preference dataset (and models).

Rigourous evaluation of LLM-synthesized code - NeurIPS 2023

CodeUltraFeedback: aligning large language models to coding preferences

Translate PDF, EPub, webpage, metadata, annotations, notes to the target language. Support 20+ translate services.

Incomplete Redis client and server implementation using Tokio - for learning purposes only

Inference code for Llama models

一份超级详细的Java面试题【大厂面试真题+Java学习指南+工作总结】

Benchmark ClassEval for class-level code generation.

Apache Lucene open-source search software

An ANTLR4 grammar for Python 3

Just Announced - "Learn Spring Security OAuth":

This is a project that show the basic idea of a lexer and a parser

ANTLR (ANother Tool for Language Recognition) is a powerful parser generator for reading, processing, executing, or translating structured text or binary files.

Produce code coverage results with gcov from afl-fuzz test cases

Curated list of project-based tutorials