The Orillusion engine is a lightweight rendering engine that fully supports the WebGPU standard. Based on the latest Web graphics API standard, a lot of explorations and attempts have been made, and many technologies and functions that were difficult or impossible to realize in the Web were realized. WebGPU support The bottom layer of the […]
RasaGPT is the first headless LLM chatbot platform built on top of Rasa and Langchain. Built-in Rasa, FastAPI, Langchain, LlamaIndex, SQLModel, pgvector, ngrok and telegram. It is a template and reference implementation for Rasa and Telegram, leveraging LLM libraries like Langchain for indexing, retrieval and context injection. RasaGPT works out of the box. characteristic: Complete
Pctrl is a robust, powerful, easy-to-use and powerful process manager based on the Rust programming language. It provides an overview of the system, such as currently running processes and systems, and gives administrators control over manipulating these processes. Pctrl aims to compete with all currently available Linux process managers by offering powerful control and a
LibYuv is a YUV conversion tool library compiled and packaged based on Google’s libyuv. Its main purpose is to perform mutual conversion, cropping, rotation, scaling, mirroring, etc. between various YUV and RGB. Gif display You can also directly download Demo App experience effect use Outline of use The functional methods in LibYuv mainly include: format
Trustfall is a query engine for querying any type of data source, from APIs and databases to any type of file on disk, even AI models. Trustfall Playground supports running queries against public data sources such as: For example, this linkShows the results of the HackerNews query: “Which GitHub or Twitter users are commenting on
ImageBind is an AI model that supports binding information from six different modalities (image, text, audio, depth, temperature, and IMU data), which unifies this information into a single embedded representation space, enabling machines to more comprehensively , learning directly from multiple information without explicit supervision (i.e., the process of organizing and labeling raw data). ImageBind
ImageBind Homepage, Documentation and Downloads- Multimodal AI Model- News Fast Delivery Read More »
Ink is a library that supports using React to build command-line applications—the same component-based UI building experience that React provides in the browser. It’s just that InK is geared towards command-line applications. So Ink is actually a React renderer, which converts the React component tree into a string, and then outputs it to the terminal.
SuperCLUE is an evaluation benchmark for general large models available in Chinese. The main question it answers is: the effect of the Chinese large-scale model under the current situation of vigorous development of the general-purpose large-scale model. including but not limited to: The effect of these models on different tasks To what extent
Chinese-LLaMA-Alpaca contains the Chinese LLaMA model and the Alpaca large model fine-tuned with instructions. Based on the original LLaMA, these models expand the Chinese vocabulary and use Chinese data for secondary pre-training, which further improves the ability to understand the basic semantics of Chinese. At the same time, the Chinese Alpaca model further uses Chinese
OpenLLaMA is an open source rendition of Meta AI’s LLaMA large language model under a permissive license. The repository contains a public preview of the trained 200 billion token 7B OpenLLaMA model, and provides PyTorch and Jax weights for the pretrained OpenLLaMA model, as well as evaluation results and comparisons to the original LLaMA model.
MLC LLM is a general solution that allows any language model to be deployed locally on various hardware backends and native applications. In addition, MLC LLM also provides an efficient framework for users to further optimize model performance according to their needs. MLC LLM is designed to enable everyone to develop, optimize and deploy AI
Base64Util canSave the file generated by Base64 decoding to the specified path; or convert the file into Base64 code, supported language: java. <!– https://mvnrepository.com/artifact/icu.xuyijie/Base64Utils –> <dependency> <groupId>icu.xuyijie</groupId> <artifactId>Base64Utils</artifactId> <version>1.2.3</version> </dependency> // 将文件编码成Base64，可传入文件全路径，或者一个 File 对象 String s = Base64Util.transferToBase64(“D:/下载/Screenshot_20221008-090627.png”); File file = new File(filePath); String s = Base64Util.transferToBase64(file); System.out.println(s); // 将Base64转换成文件保存到指定位置，可传入文件全路径或者分别传入保存位置和文件名 String s1 = Base64Util.generateFile(s, “D:/下载/aaa.png”);
Base64Util Homepage, Documentation and Download – Base64 Codec Tool – News Fast Delivery Read More »
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
SantaCoder is a language model with 1.1 billion parameters that can be used for code generation and completion suggestions in several programming languages such as Python, Java, and JavaScript. According to the official information, the basis for training SantaCoder is The Stack (v1.1) data set. Although SantaCoder is relatively small in size, with only 1.1
