Zhejiang University Graduation Thesis LaTeX Template

OceanGym: A Benchmark Environment for Underwater Embodied Agents

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

adds Sequence Parallelism into LLaMA-Factory

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

The official repository of the dots.llm1 base and instruct models proposed by rednote-hilab.

Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team, Alibaba Cloud.

ChineseHarm-Bench: A Chinese Harmful Content Detection Benchmark

Interpretable data visualizations for understanding how texts differ at the word level

StyleLLM文风大模型：基于大语言模型的文本风格迁移项目。Text style transfer base on Large Language Model. #文字修饰 # 润色 #风格模仿

【ACL 2024】 SALAD benchmark & MD-Judge

[ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data generation pipeline!

SCCD:基于会话的中文网络欺凌检测数据集

Set of tools to assess and improve LLM security.

轻量超严格敏感词库

中文 Instruction tuning datasets

Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

Attention is all you need implementation

Code for SafeMERGE (ICLR 2025).

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

LLM大模型（重点）以及搜广推等 AI 算法中手写的面试题，（非 LeetCode），比如 Self-Attention, AUC等，一般比 LeetCode 更考察一个人的综合能力，又更贴近业务和基础知识一点