Documentação e arquivos de configuração para participação no Piloto do Real DigitalKit Onboarding - Piloto Real Digital Este repositório contém as informações necessárias para a participação no piloto do Real Digital. A documentação será complementada conforme o feedback dos participantes. Arquitetura do Piloto Conexão com a rede do Real Digital Smart Contracts Exemplos de interação com os smart contracts
The Multi-Agent Meta Programming Framework: Given one line Requirement, return PRD, Design, Tasks, Repo | 多智能体元编程框架：给定老板需求，输出产品文档、架构设计、任务列表、代码MetaGPT: Multi-Agent Meta Programming Framework Assign different roles to GPTs to form a collaborative software entity for complex tasks. MetaGPT takes a one line requirement as input and outputs user stories / competitive analysis / requirements / data structures / APIs / documents, etc. Internally, MetaGPT includes product managers / arch…
中文法律大模型ChatLaw-法律大模型 但愿世间不纷争，何惜法典卷生尘 易用 / 简单 / 快速 arXiv · 在线体验 ChatLaw系列模型 ChatLaw-13B，此版本为学术demo版，基于姜子牙Ziya-LLaMA-13B-v1训练而来，中文各项表现很好，但是逻辑复杂的法律问答效果不佳，需要用更大参数的模型来解决。 ChatLaw-33B，此版本为学术demo版，基于Anima-33B训练而来，逻辑推理能力大幅提升，但是因为Anima的中文语料过少，导致问答时常会出现英文数据。 ChatLaw-Text2Vec，使用93w条判决案例做成的数据集基于BERT训练了一个相似度匹配模型，可将用户提问信息和对应的法条相匹配，例如： “请问如果借款没还怎么办…
Starting kit for the NeurIPS 2023 unlearning challenge Starting kit for the NeurIPS 2023 Machine Unlearning Challenge This repository contains the starting kit for the NeurIPS 2023 Machine Unlearning Challenge. The starting kit currently contains the following examples: Unlearning on CIFAR10 The notebook unlearning-CIFAR10.ipynb provides a foundation for participants to build their unlearning models on the CIFAR-10 dataset. This jupyter notebook can be run locally, on Colab, or on Kaggle
Extension to return old Twitter layout from 2015.OldTwitter (2023) Browser extension to return old Twitter layout from 2015. This extension doesn't add any CSS on top of original Twitter. It's fully original client that replaces Twitter, making it much faster than alternatives. Installation Chrome, Opera, Brave & Chromium browsers: Chrome Web Store Firefox: Addons For Firefox Edge: Microsoft Edge Addons Donate If you like this extension please consider donating: https://dimden.dev/…
Open Source Education PlatformNoodle Noodle is an open source student productivity platform that helps students manage everything to do with their education from tasks, notes, flash cards to timetables. We are rethinking student productivity with Noodle. Noodle is still in early development and is not ready for use yet. Follow me on twitter @ixahmedxii for updates. Purpose Typically for a student, you need to be using multiple applications just to be managing your education well. This would …
aider is GPT powered coding in your terminalaider is GPT powered coding in your terminal aider is a command-line chat tool that allows you to write and edit code with OpenAI's GPT models. You can ask GPT to help you start a new project, or modify code in your existing git repo. Aider makes it easy to git commit, diff & undo changes proposed by GPT without copy/pasting. It also has features that help GPT-4 understand and modify larger codebases. Getting started Example chat transcript…
C++ implementation of ChatGLM-6B & ChatGLM2-6BChatGLM.cpp C++ implementation of ChatGLM-6B and ChatGLM2-6B for real-time chatting on your MacBook. Features Pure C++ implementation based on ggml, working in the same way as llama.cpp. Accelerated memory-efficient CPU inference with int4/int8 quantization, optimized KV cache and parallel computing. Streaming generation with typewriter effect. Python binding, web demo, and more possibilities. Getting Started Preparation Clone the ChatGLM.c…
OpenChat: Less is More for Open-source ModelsOpenLLMs: Less is More for Open-source Models OpenLLMs is a series of open-source language models fine-tuned on a small, yet diverse and high-quality dataset of multi-round conversations. Specifically, we utilize only ~6K GPT-4 conversations directly filtered from the ~90K ShareGPT conversations. Despite the small size of the dataset, OpenLLMs has demonstrated remarkable performance. 🔥 80.9% win-rate, rank #1 of open-source models on AlpacaEval 🚀 105…