Stars
Tools for merging pretrained large language models.
Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.
CLUENER2020 中文细粒度命名实体识别 Fine Grained Named Entity Recognition
A neural network model for Chinese named entity recognition
Universal cross-platform tokenizers binding to HF and sentencepiece
AI Code Review is a lightweight, simple GitHub Action that supports various AI models to analyze and provide feedback on your code. This GitHub Action helps improve code quality by automatically re…
🐎 A fast implementation of the Aho-Corasick algorithm using the compact double-array data structure in Rust.
C/C++ JSON parser/generator benchmark
A cross-platform `addr2line` clone written in Rust, using `gimli`
📦 CMake's missing package manager. A small CMake script for setup-free, cross-platform, reproducible dependency management.
HTTP load testing tool and library. It's over 9000!
Successor of https://sourceforge.net/projects/libdxfrw/, developed for LibreCAD, by LibreCAD Contributors, usable for all
go 实现的压测工具，ab、locust、Jmeter压测工具介绍【单台机器100w连接压测实战】
超轻量级中文ocr，支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M
A simple OCR API server, seriously easy to be deployed by Docker, on Heroku as well
A fast inference library for running LLMs locally on modern consumer-class GPUs
加大模型最大 Token 序列长度（位置嵌入长度）的工具. A tool extending model position embedding length (maximum Token sequence length)
本项目旨在收集开源的表格智能任务数据集（比如表格问答、表格-文本生成等），将原始数据整理为指令微调格式的数据并微调LLM，进而增强LLM对于表格数据的理解，最终构建出专门面向表格智能任务的大型语言模型。
code for piccolo embedding model from SenseTime
Awesome Pretrained Chinese NLP Models，高质量中文预训练模型&大模型&多模态模型&大语言模型集合
An Efficient "Factory" to Build Multiple LoRA Adapters
AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.