Starred repositories
Full stack, modern web application template. Using FastAPI, React, SQLModel, PostgreSQL, Docker, GitHub Actions, automatic HTTPS and more.
基于 FastAPI 构建的前后端分离 RBAC 权限控制系统,采用独特的伪三层架构模型设计,内置 fastapi-admin 基本实现,并作为模板库免费开源;FastAPI based on the construction of the front and back end separation of RBAC privilege control system, using a uniq…
FastAPI Best Practices and Conventions we used at our startup
“连续八年成为全世界最受喜爱的语言,无 GC 也无需手动内存管理、极高的性能和安全性、过程/OO/函数式编程、优秀的包管理、JS 未来基石" — 工作之余的第二语言来试试 Rust 吧。本书拥有全面且深入的讲解、生动贴切的示例、德芙般丝滑的内容,这可能是目前最用心的 Rust 中文学习教程 / Book
Learning Rust By Practice, narrowing the gap between beginner and skilled-dev through challenging examples, exercises and projects.
deep learning for image processing including classification and object-detection etc.
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库;24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
🎉 Repo for LaWGPT, Chinese-Llama tuned with Chinese Legal knowledge. 基于中文法律知识的大语言模型
Train transformer language models with reinforcement learning.
A series of large language models developed by Baichuan Intelligent Technology
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
A cloud-native vector database, storage for next generation AI applications
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
中文 NLP 预处理、解析工具包,准确、高效、易用 A Chinese NLP Preprocessing & Parsing Package www.jionlp.com
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Human ChatGPT Comparison Corpus (HC3), Detectors, and more! 🔥
Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.
Chinese-LLaMA 1&2、Chinese-Falcon 基础模型;ChatFlow中文对话模型;中文OpenLLaMA模型;NLP预训练/指令微调数据集
Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins
Instruct-tune LLaMA on consumer hardware with shareGPT data
基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型,进行下游具体任务微调,涉及Freeze、Lora、P-tuning、全参微调等
chatglm 6b finetuning and alpaca finetuning
use chatGLM to perform text embedding