== My new service == 🧑💻 == My main business website == 🧑💻 I’m open to freelancing work 🙂 and feel free to reach out even if you just have a WordPress-related question. Questions from you may become a new video here. I love to connect with business owners who regularly use WordPress. #wordpress #webdevelopment […]
Get our Awesome ‘How to Build an Elementor Website Course’ – Lifetime Updates and access to New Modules at no extra cost: Join our ‘How to Start a Web Design Business’ Course – and use strategies to grow, get clients, and generate recurring income: Book your 1-2-1 Consultation: LPagery is an awesome way to build
Quivr is a knowledge base solution powered by generative AI to store and retrieve unstructured information. Quivr supports uploading text, images, videos, code snippets, PPT, Excel data sheets and other content directly to the cloud database, and quickly realizes information retrieval and question answering through large language models such as GPT-4. Quivr supports large language
STDF is a mobile page component library based on Svelte and Tailwind. characteristic No runtime, no virtual DOM, faster online operation; Rich API, easy to configure component styles that meet the needs; Based on Svelte and Tailwind, coding is fast and easy; Support dark mode; Provide rich Chinese and English
GraphLearn-for-PyTorch (GLT) is a PyTorch-based graph learning library that aims to make distributed GNN training and inference easy and efficient. GLT utilizes GPU-accelerated graph sampling and utilizes UVA to reduce the transformation and duplication of vertex and edge features. For large-scale graphs, it supports distributed training on multiple GPUs or multiple machines through efficient distributed
vue-big-screen is a “big data screen project” based on Vue, Datav, and Echart frameworks. It uses Vue components to dynamically refresh and render data, and internal charts can be freely replaced. Some charts use DataV’s own components and can be changed. Project display Main file introduction File function/function main.js main directory file, import Echart/DataV and
Vue-big-screen data big screen project based on Vue Read More »
YuLan-Chat is a large language dialogue model fine-tuned based on high-quality Chinese-English mixed instructions. YuLan-Chat uses LLaMA as the base, fine-tuned with well-optimized high-quality Chinese-English mixed instructions. Among them, the YuLan-Chat-65B model can significantly surpass the performance of existing open source models on Chinese and English related evaluation data sets. The team said that it
Speeduino is a flexible, full-featuredengine management system(EMS). It provides the hardware, firmware and software components that make up the engine management system, all available under open licenses. The various components that make up the system: Speeduino board:This is the main body of the Speeduino ECU, containing all drivers and IO circuits. Arduino:This is the brain
SRAAL is an open-source code for an adversarial active learning algorithm based on state relabeling. The algorithm describes active learning in the case of limited data labeling budget. The generative model VAE is used to carry out unsupervised feature reconstruction learning based on the variational process on the data, and the state relabeling method is
Twelvet is a permission management system based on Spring Cloud Alibaba. It integrates popular libraries on the market and can be used as a framework for rapid development. A set of scaffolding based on microservice architecture, using the Spring Cloud Alibaba series for architecture, learning and understanding it will enable you to quickly grasp the
LaWGPT is a series of open source large language models based on Chinese legal knowledge. This series of models is based on the general Chinese base model (such as Chinese-LLaMA, ChatGLM, etc.)Large-scale Chinese legal corpus pre-training, which enhances the basic semantic understanding ability of large models in the legal field. on the basis of,Construct a
WizardLM is a fine-tuned 7B LLaMA model. It fine-tunes following the dialogue through a large number of commands of varying difficulty. The novelty of this model is the use of LLM to automatically generate training data. The WizardLM model uses a new method called Evol-Instruct (a new method to improve the ability of LLM by
Chinese-Vicuna is a Chinese low-resource LLaMA+Lora solution.Project includes code for finetune model code for inference using only CPU code for inference (using C++) tools for downloading/converting/quantizing Facebook llama.ckpt other apps #ChineseVicuna #large #Chinese #language #model #based #LLaMA
Chinese-Vicuna, a large Chinese language model based on LLaMA Read More »
Clash is a rule-based tunneling for Go. characteristic: Native HTTP/HTTPS/SOCKS server with authentication support Shadowsocks(R), VMess, Trojan, Snell, SOCKS5, HTTP(S) outbound support built-infake IP DNS server designed to minimize the impact of DNS pollution attacks. Support for DoH/DoT upstream. Route packets to different destinations based on domain, GEOIP, IP-CIDR or process
