This repository is a curated list of resources for Large Language Models (LLMs), covering milestone papers, frameworks, tools, datasets, evaluation benchmarks, courses, and publicly available checkpoints and APIs. It serves as a comprehensive knowledge base for researchers, developers, and enthusiasts interested in the rapidly evolving field of LLMs, providing a structured overview of key advancements and practical resources.

How It Works

The repository organizes information into distinct categories, including milestone papers that trace the historical development of LLMs, and a broad collection of other papers categorized by subfields like hallucination detection, instruction tuning, and LLM systems. It also lists prominent LLM leaderboards, open LLM projects, data resources, evaluation frameworks, training frameworks, inference tools, and application examples.

Quick Start & Requirements

This is a curated list, not a software package. No installation or execution is required. All resources are linked for direct access.

Highlighted Details

• Extensive historical timeline of LLM milestone papers from 2017 to present.
• Comprehensive lists of LLM projects, including recent trending models like DeepSeek-V3 and Qwen2.5.
• Detailed sections on LLM evaluation benchmarks, training frameworks, and inference solutions.
• A vast collection of links to papers, tutorials, courses, and books on LLMs.

Maintenance & Community

The repository is actively maintained, with frequent updates reflecting the latest LLM research and releases. Contributions are welcomed via pull requests. Contact information for the maintainer is provided.

Licensing & Compatibility

The repository itself is a list of links and does not have a specific software license. Individual resources linked may have their own licenses.

Limitations & Caveats

As a curated list, the quality and relevance of linked resources depend on the maintainer's selection. The sheer volume of information may require significant effort to navigate and digest fully.