LXGW Neo ZhiSong / 夏鹿新zhi宋 is a Chinese Song typeface derived from “IPAmj Ming Dynasty”. According to reports, Xia Dong Xinzhi Song is based on “IPAmj Ming Dynasty”, which is an attempt to transform the Japanese writing style into the standard Chinese writing style. Xiadong Xinzhisong is a sister font of “Xiadong Xinxihei”, trying to […]
IoTOS is an efficient and practical IoTCard management & operation system. IoTOS is currently named too broadly, and it is mainly used for IoT Card management business with efficient, robust, and flexible design of SaaS, multi-language, robot push, automatic management, and data synchronization multi-type algorithms as the main business. 1.1 Introduction IoTOS is
FinGPT is a large-scale pre-trained language model in the financial field. It can understand and generate financial news, analyze public sentiment on social media, interpret financial reports such as annual reports, quarterly earnings reports, etc., make market forecasts, and provide personalized investment advice by learning users’ personal preferences. The training data for FinGPT comes from
I-JEPA is a method for self-supervised learning. At a high level, I-JEPA predicts a representation of one part of an image from representations of other parts of the same image. Notably, this approach learns semantic image features: Do not rely on pre-specified invariants for hand-crafted data transformations, which tend to be biased towards specific
YouTube to CUE is a converter, as you can tell from the name, it can convert YouTube to CUE. This program is designed to download audio albums from YouTube. It uses YouTube-DL (or yt-dlp) to download audio files and generate a Cue Sheet with metadata. Require: – GNU Linux or FreeBSD– youtube-dl >= 2021.06.60 or
LangKit is an open source text metrics toolkit for monitoring language models. It provides a set of methods for extracting relevant signals from input and/or output text, which are compatible with the open source datalogging library whylogs. Currently supported metrics include: Text Quality Readability Score Complexity and Grade Score Text Relevance Similarity Score Between Prompts/Responses
Make large language models safe and reliable LangKit Read More »
JupyterLab Desktop is a cross-platform desktop application for JupyterLab. It’s the fastest and easiest way to start using Jupyter Notebook on your PC, with flexibility for advanced use cases. Install Debian, Ubuntu Linux installer Red Hat, Fedora, SUSE Linux installer macOS Intel installer, macOS Apple silicon installer Windows installer Additionally, JupyterLab can be installed on
baichuan-7B is an open source large-scale pre-training model, based on the Transformer structure, a 7 billion parameter model trained on about 1.2 trillion tokens, supports Chinese and English bilingual, and the context window length is 4096. The overall model is based on the standard Transformer structure, using the same model design as LLaMA Location code:rotary-embeddingIt
TypeCell is an open source Typescript real-time programming environment. Designed to make it easier to build software, and ultimately make it easier to understand, build, and share knowledge. Features: Open source, cell-based notebook environment same as VS Code, powerful editing experience Full TypeScript support! (No weird custom language constructs) Reactive runtime, cells are automatically re-evaluated
Typescript real-time programming environment TypeCell Read More »
CloudFoundry User Account and Authentication (UAA) Server is a key component of the CloudFoundry platform, which provides user authentication and authorization services, and supports multiple identity providers and authentication protocols. UAA Server can be used to manage authentication and authorization of entities such as users, organizations, and service instances. It supports protocols such as OAuth2
Informed is a lightweight framework for building forms in React applications. Out of the box, it supports getting and manipulating values, validating fields, creating custom inputs, multi-step forms, array fields, and more. example // Example.jsx import { Relevant, Debug } from ‘informed’; // Inputs that were hooked up to informed via “useField”
OpenBuddy is a powerful open source multilingual chatbot model for global users, with a strong emphasis on conversational AI and seamless multilingual support, including English, Chinese and other languages. Based on Tii’s Falcon model and Facebook’s LLaMA model, OpenBuddy has been fine-tuned, including expanding the vocabulary, adding common characters and enhancing token embedding. By leveraging
Rust, Python, and gRPC servers for text generation inference. Used in production by HuggingFace to power LLM’s api inference widget. Features: Serve the most popular large-scale language models using a simple launcher Tensor Parallelism for faster inference on multiple GPUs Continuously batch incoming requests using token streaming of Server-Sent Events (SSE) to improve overall performance
Large language model text generation reasoning Text Generation Inference Read More »
M3E is the abbreviation of Moka Massive Mixed Embedding Moka, this model is trained by MokaAI, open source and evaluation, used by training script uniem to evaluate BenchMark using MTEB-en Massive, this model passestens of millions (2200w+) Chinese sentences are trained on the data set Mixed, this model supports bilingual homogeneous text
