🚀 下一代 AI 一站式解决方案，一站式 Chat + 中转 API 站点，支持 OpenAI，Midjourney，Claude，讯飞星火，Stable Diffusion，DALL·E，ChatGLM，通义千问，腾讯混元，360 智脑，百川 AI，火山方舟，新必应，Google Gemini (PaLM2)，Moonshot，LocalAI 等模型，支持对话分享，自定义预设，云端同步，模型市场，支持弹性计费 / 订阅计划模式，支持图片解析，支持联网搜索，支持模型缓存，丰富美观的后台管理与仪表盘数据统计。 Chat Nio 🚀 下一代 AI 一站式解决方案 🚀 Next Generation AI One-Stop Solution 官网 | 开放文档 | SDKs | QQ 群 📝 功能 ✨ AI 聊天对话功能 丰富格式兼容 支持 Vision 模型, 同时支持 直接上传图片 和 输入图片直链或 Base64 图片 功能 (如 GPT-4 Vision Preview, Gemini Pro Vision 等模型) 支持 DALL-E 模型绘图 支持 Midjourn…
Training LLMs with QLoRA + FSDPfsdp_qlora Training LLMs with Quantized LoRA + FSDP. Read our announcement blog post. You should treat this script as an alpha/preview release. If you’re not comfortable with testing and debugging models, we’d suggest holding off for a few months while the community more fully tests the approach. Installation The following steps should work (tested on Cuda 11.7, 11.8 and 12.1): Clone https://github.com/AnswerDotAI/fsdp_qlora pip install llama-recipes fastcore --e…
Learning English through the method of constructing sentences with conjunctions Earthworm English | 中文 ⚡ Introduction By constructing sentences with conjunctions, it helps you learn English better~ 😊 🚀 How to start ? ⚠️ Requirements pnpm version >= 8 Node.js version >= v20 MySQL version >= 8.0.0 Redis version >= 5.0.0 Docker. please make sure it is installed and running successfully on your local machine. The mentioned operations below are based on the root directory of the…
A distributed, fault-tolerant task queue A Distributed, Fault-Tolerant Task Queue Documentation · Website · Issues What is Hatchet? Hatchet replaces difficult to manage legacy queues or pub/sub systems so you can design durable workloads that recover from failure and solve for problems like concurrency, fairness, and rate limiting. Instead of managing your own task queue or pub/sub system, you can use Hatchet to distribute your functions betwe…
Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdfAQLM Official PyTorch implementation for Extreme Compression of Large Language Models via Additive Quantization Inference Demo Learn how to run the prequantized models using this Google Colab examples: Basic AQLM generation Streaming with GPU/CPU Inference with CUDA graphs (3x speedup) Fine-tuning with PEFT Models This repository is current…
Go ahead and axolotl questionsAxolotl Axolotl is a tool designed to streamline the fine-tuning of various AI models, offering support for multiple configurations and architectures. Features: Train various Huggingface models such as llama, pythia, falcon, mpt Supports fullfinetune, lora, qlora, relora, and gptq Customize configurations using a simple yaml file or CLI overwrite Load different dataset formats, use custom formats, or bring your own tokenized datasets Integrated with xformer, flash…
Fast Rust bundler for JavaScript with Rollup-compatible API. 🚧 Work in Progress Rolldown is currently in active development and not usable for production yet. Rolldown Rolldown is a JavaScript bundler written in Rust intended to serve as the future bundler used in Vite. It provides Rollup-compatible APIs and plugin interface, but will be more similar to esbuild in scope. For more information, please check out the documentation at rolldown.rs. Contributing We would love to have mor…
Farm 🍅 on the Fuel network.sway-farm A simple farming game written in Sway. Running Locally Make sure you have fuelup installed and are using the beta-5 toolchain. Install the Fuel Wallet extension and copy your wallet address. In the frontend folder, open the src/App.tsx file and add the following lines using your Fuel wallet address: const myWallet = new WalletLocked("fuel123...."); console.log("WALLET:", myWallet.address.toB256()); Run the frontend locally with npm start, and…
An open source wearable with cameraWhomane: Open-Source AI Wearable with a Camera No Case With case See online Demo Our vision is to make wearable AI accessible to everyone, to use and to build on. Our mission is to provide the tools and support, so that you can focus on what matters. Be apart of the revolution! Whomane is here to stay, at the forefront of AI hardware innovation. Getting Started Follow these steps to get started with Whomane: Clone/Host the Web App Buy/Assembl…