OpenCompass is an LLM evaluation platform, supporting a wide range of models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek, etc, across 100+ datasets covering knowledge, reasoning, coding, sc…

向量检索与 RAG 实践：技术、实现与应用

搜索所有中文NLP数据集，附常用英文NLP数据集

仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理

从零实现一个小参数量中文大语言模型。

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

This is a repository used by individuals to experiment and reproduce the pre-training process of LLM.

Arena-Hard-Auto: An automatic LLM benchmark.

Model Context Protocol Servers

复现大模型相关算法及一些学习记录

Hierarchical Reasoning Model Official Release

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI