sawyerbutton's repositories
NLP-Funda-2023-Spring
2023 Sping NLP Fundamental Course
NLP-Funda-2024-Spring
NLP Fundamental Course for 2024 Spring
LM-Funda-2024-Spring
Large Model Courses for 2024 Spring
NLP-Lesson-3-Scrapy
Scrapy Starter project
Medical-Rumor-Explanation
Medical Rumor Explanation Pipeline
2023-kaggle-ai-report
https://www.kaggle.com/competitions/2023-kaggle-ai-report realate repo
chatGLM-6B-QLoRA
使用peft库,对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调,并做lora model和base model的merge及4bit的量化(quantize)。
chatgpt-api-server
ChatGPT Web API server based on Flask that can respond both via browser through Flask Forms and directly via POST/GET Requests
DailyPaper
By crawling the latest papers on arXiv with specified keywords using a web crawler, and then summarizing the content of the papers using chatgpt, we can compile and update the information.通过爬虫每日抓取arXiv上指定关键词的最新论文,然后使用chatgpt总结论文内容,汇总更新。
gpt-engineer
Specify what you want it to build, the AI asks for clarification, and then builds it.
gpt_academic
为GPT/GLM提供图形交互界面,特别优化论文阅读润色体验,模块化设计支持自定义快捷按钮&函数插件,支持代码块表格显示,Tex公式双显示,新增Python和C++项目剖析&自译解功能,PDF/LaTex论文翻译&总结功能,支持并行问询多种LLM模型,支持清华chatglm等本地模型。兼容复旦MOSS, llama, rwkv, 盘古等。
how-to-train-tokenizer
怎么训练一个LLM分词器
langchain-ChatGLM
langchain-ChatGLM, local knowledge based ChatGLM with langchain | 基于本地知识库的 ChatGLM 问答
llama-recipes
Examples and recipes for Llama model
material.github.io
Angular Material 中文版程序(外壳)
memoReminder-createdByChatGPT
A memoReminder created by ChatGPT with prompting to improve
MetaGPT
🌟 The Multi-Agent Meta Programming Framework: Given one line Requirement, return PRD, Design, Tasks, Repo
Nest-Gateway
Using NestJS based on fastify to build a gateway system for begineer
ng-zorro-antd
An enterprise-class UI components based on Ant Design and Angular. 🐜
NLP-Fundamental
NLP Fundamental Sharing
Promptspot
Prompt testing made easy
streamlit-agent
Reference implementations of several LangChain agents as Streamlit apps
torchkeras
Pytorch❤️ Keras 😋😋
tree-of-thoughts
Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%
tuning_playbook
A playbook for systematically maximizing the performance of deep learning models.