WeClone is a tool that fine-tunes large language models using WeChat chat records. It utilizes approximately 20,000 integrated and effective data points, resulting in somewhat satisfactory outcomes that are occasionally humorous. The tool's effectiveness largely depends on the quantity and quality of the chat data provided. It requires a minimum of 16GB of GPU memory for training using the default chatglm3-6b model with LoRA method. Users can also opt for other models and methods supported by LLAMA Factory, which consume less memory. The tool has specific hardware and software requirements, including Python, Torch, Transformers, Datasets, Accelerate, and other optional packages like CUDA and Deepspeed. The tool facilitates environment setup, data preparation, data preprocessing, model downloading, parameter configuration, model fine-tuning, and inference through a browser demo or API service. Additionally, it offers the ability to deploy a WeChat chatbot, although users should be cautious due to the risk of account suspension by WeChat.

Video-subtitle-remover (VSR) is a software based on AI technology that removes hard subtitles from videos. It achieves the following functions: - Lossless resolution: Remove hard subtitles from videos, generate files with subtitles removed - Fill the region of removed subtitles using a powerful AI algorithm model (non-adjacent pixel filling and mosaic removal) - Support custom subtitle positions, only remove subtitles in defined positions (input position) - Support automatic removal of all text in the entire video (no input position required) - Support batch removal of watermark text from multiple images.

Tiny LLM zh is a project aimed at building a small-parameter Chinese language large model for quick entry into learning large model-related knowledge. The project implements a two-stage training process for large models and subsequent human alignment, including tokenization, pre-training, instruction fine-tuning, human alignment, evaluation, and deployment. It is deployed on ModeScope Tiny LLM website and features open access to all data and code, including pre-training data and tokenizer. The project trains a tokenizer using 10GB of Chinese encyclopedia text to build a Tiny LLM vocabulary. It supports training with Transformers deepspeed, multiple machine and card support, and Zero optimization techniques. The project has three main branches: llama2_torch, main tiny_llm, and tiny_llm_moe, each with specific modifications and features.

This repository provides a demonstration of running a native Large Language Model (LLM) on Android devices. It supports various models such as Qwen2.5-Instruct, MiniCPM-DPO/SFT, Yuan2.0, Gemma2-it, StableLM2-Chat/Zephyr, and Phi3.5-mini-instruct. The demo models are optimized for extreme execution speed after being converted from HuggingFace or ModelScope. Users can download the demo models from the provided drive link, place them in the assets folder, and follow specific instructions for decompression and model export. The repository also includes information on quantization methods and performance benchmarks for different models on various devices.

The WeChat Markdown editor automatically renders Markdown documents as WeChat articles, eliminating the need to worry about WeChat content layout! As long as you know basic Markdown syntax (now with AI, you don't even need to know Markdown), you can create a simple and elegant WeChat article. The editor supports all basic Markdown syntax, mathematical formulas, rendering of Mermaid charts, GFM warning blocks, PlantUML rendering support, ruby annotation extension support, rich code block highlighting themes, custom theme colors and CSS styles, multiple image upload functionality with customizable configuration of image hosting services, convenient file import/export functionality, built-in local content management with automatic draft saving, integration of mainstream AI models (such as DeepSeek, OpenAI, Tongyi Qianwen, Tencent Hanyuan, Volcano Ark, etc.) to assist content creation.

ChatTTS-Forge is a powerful text-to-speech generation tool that supports generating rich audio long texts using a SSML-like syntax and provides comprehensive API services, suitable for various scenarios. It offers features such as batch generation, support for generating super long texts, style prompt injection, full API services, user-friendly debugging GUI, OpenAI-style API, Google-style API, support for SSML-like syntax, speaker management, style management, independent refine API, text normalization optimized for ChatTTS, and automatic detection and processing of markdown format text. The tool can be experienced and deployed online through HuggingFace Spaces, launched with one click on Colab, deployed using containers, or locally deployed after cloning the project, preparing models, and installing necessary dependencies.

AI Daily Digest is a tool that fetches the latest articles from the top 90 Hacker News technology blogs recommended by Andrej Karpathy. It uses AI multi-dimensional scoring to curate a structured daily digest. The tool supports Gemini by default and can automatically degrade to OpenAI compatible API. It offers a five-step processing pipeline including RSS fetching, time filtering, AI scoring and classification, AI summarization and translation, and trend summarization. The generated daily digest includes sections like today's highlights, must-read articles, data overview, and categorized article lists. The tool is designed to be dependency-free, bilingual, with structured summaries, visual statistics, intelligent categorization, trend insights, and persistent configuration memory.

LM Engine is a research-grade, production-ready library for training large language models at scale. It provides support for multiple accelerators including NVIDIA GPUs, Google TPUs, and AWS Trainiums. Key features include multi-accelerator support, advanced distributed training, flexible model architectures, HuggingFace integration, training modes like pretraining and finetuning, custom kernels for high performance, experiment tracking, and efficient checkpointing.

LLMIO is a Go-based LLM load balancing gateway that provides a unified REST API, weight scheduling, logging, and modern management interface for your LLM clients. It helps integrate different model capabilities from OpenAI, Anthropic, Gemini, and more in a single service. Features include unified API compatibility, weight scheduling with two strategies, visual management dashboard, rate and failure handling, and local persistence with SQLite. The tool supports multiple vendors' APIs and authentication methods, making it versatile for various AI model integrations.

Chinese-Mixtral-8x7B is an open-source project based on Mistral's Mixtral-8x7B model for incremental pre-training of Chinese vocabulary, aiming to advance research on MoE models in the Chinese natural language processing community. The expanded vocabulary significantly improves the model's encoding and decoding efficiency for Chinese, and the model is pre-trained incrementally on a large-scale open-source corpus, enabling it with powerful Chinese generation and comprehension capabilities. The project includes a large model with expanded Chinese vocabulary and incremental pre-training code.

ReGraph is a decentralized AI compute marketplace that connects hardware providers with developers who need inference and training resources. It democratizes access to AI computing power by creating a global network of distributed compute nodes. It is cost-effective, decentralized, easy to integrate, supports multiple models, and offers pay-as-you-go pricing.

Clother is a command-line tool that allows users to switch between different Claude Code providers instantly. It provides launchers for various cloud, open router, China endpoints, local, and custom providers, enabling users to configure, list profiles, test connectivity, check installation status, and uninstall. Users can also change the default model for each provider and troubleshoot common issues. Clother simplifies the management of API keys and installation directories, supporting macOS, Linux, and Windows (WSL) platforms. It is designed to streamline the workflow of interacting with different AI models and services.

ChatMASTER is a self-built backend conversation service based on AI large model APIs, supporting synchronous and streaming responses with perfect printer effects. It supports switching between mainstream models such as DeepSeek, Kimi, Doubao, OpenAI, Claude3, Yiyan, Tongyi, Xinghuo, ChatGLM, Shusheng, and more. It also supports loading local models and knowledge bases using Ollama and Langchain, as well as online API interfaces like Coze and Gitee AI. The project includes Java server-side, web-side, mobile-side, and management background configuration. It provides various assistant types for prompt output and allows creating custom assistant templates in the management background. The project uses technologies like Spring Boot, Spring Security + JWT, Mybatis-Plus, Lombok, Mysql & Redis, with easy-to-understand code and comprehensive permission control using JWT authentication system for multi-terminal support.

Pi-Browser is a CLI tool for automating browsers based on multiple AI models. It supports various AI models like Google Gemini, OpenAI, Anthropic Claude, and Ollama. Users can control the browser using natural language commands and perform tasks such as web UI management, Telegram bot integration, Notion integration, extension mode for maintaining Chrome login status, parallel processing with multiple browsers, and offline execution with the local AI model Ollama.

FLUTE (Flexible Lookup Table Engine for LUT-quantized LLMs) is a tool designed for uniform quantization and lookup table quantization of weights in lower-precision intervals. It offers flexibility in mapping intervals to arbitrary values through a lookup table. FLUTE supports various quantization formats such as int4, int3, int2, fp4, fp3, fp2, nf4, nf3, nf2, and even custom tables. The tool also introduces new quantization algorithms like Learned Normal Float (NFL) for improved performance and calibration data learning. FLUTE provides benchmarks, model zoo, and integration with frameworks like vLLM and HuggingFace for easy deployment and usage.

RunAnywhere is an on-device AI tool for mobile apps that allows users to run LLMs, speech-to-text, text-to-speech, and voice assistant features locally, ensuring privacy, offline functionality, and fast performance. The tool provides a range of AI capabilities without relying on cloud services, reducing latency and ensuring that no data leaves the device. RunAnywhere offers SDKs for Swift (iOS/macOS), Kotlin (Android), React Native, and Flutter, making it easy for developers to integrate AI features into their mobile applications. The tool supports various models for LLM, speech-to-text, and text-to-speech, with detailed documentation and installation instructions available for each platform.

Deploy langgenius/dify, an LLM based chat bot app on kubernetes with helm chart.

Next.js AI Chatbot is an open-source app template for building AI chatbots using Next.js, Vercel AI SDK, OpenAI, and Vercel KV. It includes features like Next.js App Router, React Server Components, Vercel AI SDK for streaming chat UI, support for various AI models, Tailwind CSS styling, Radix UI for headless components, chat history management, rate limiting, session storage with Vercel KV, and authentication with NextAuth.js. The template allows easy deployment to Vercel and customization of AI model providers.

The ChatGPT Telegram Bot is a powerful Telegram bot that utilizes various GPT models, including GPT3.5, GPT4, GPT4 Turbo, GPT4 Vision, DALL·E 3, Groq Mixtral-8x7b/LLaMA2-70b, and Claude2.1/Claude3 opus/sonnet API. It enables users to engage in efficient conversations and information searches on Telegram. The bot supports multiple AI models, online search with DuckDuckGo and Google, user-friendly interface, efficient message processing, document interaction, Markdown rendering, and convenient deployment options like Zeabur, Replit, and Docker. Users can set environment variables for configuration and deployment. The bot also provides Q&A functionality, supports model switching, and can be deployed in group chats with whitelisting. The project is open source under GPLv3 license.

This repository showcases how to build a simple LLM-based chatbot for answering questions based on documents using retrieval augmented generation (RAG) technique. It also provides guidance on deploying the chatbot using Podman or on the OpenShift Container Platform. The workshop associated with this repository introduces participants to LLMs & RAG concepts and demonstrates how to customize the chatbot for specific purposes. The software stack relies on open-source tools like streamlit, LlamaIndex, and local open LLMs via Ollama, making it accessible for GPU-constrained environments.

LangChat is an enterprise AIGC project solution in the Java ecosystem. It integrates AIGC large model functionality on top of the RBAC permission system to help enterprises quickly customize AI knowledge bases and enterprise AI robots. It supports integration with various large models such as OpenAI, Gemini, Ollama, Azure, Zhifu, Alibaba Tongyi, Baidu Qianfan, etc. The project is developed solely by TyCoding and is continuously evolving. It features multi-modality, dynamic configuration, knowledge base support, advanced RAG capabilities, function call customization, multi-channel deployment, workflows visualization, AIGC client application, and more.

The ai-sdk-chrome-ai repository is an open-source chatbot built with Next.js, the Vercel AI SDK, and the Chrome AI provider. It features Next.js App Router, Vercel AI SDK for interacting with the Gemini Nano model, shadcn/ui, Tailwind CSS styling, and Radix UI for headless component primitives. Users can deploy their own version of the chatbot to Vercel with one click and run it locally by installing dependencies and running the dev server. The repository provides a template for creating and customizing a chatbot powered by AI technology.

WeClone is a tool that fine-tunes large language models using WeChat chat records. It utilizes approximately 20,000 integrated and effective data points, resulting in somewhat satisfactory outcomes that are occasionally humorous. The tool's effectiveness largely depends on the quantity and quality of the chat data provided. It requires a minimum of 16GB of GPU memory for training using the default chatglm3-6b model with LoRA method. Users can also opt for other models and methods supported by LLAMA Factory, which consume less memory. The tool has specific hardware and software requirements, including Python, Torch, Transformers, Datasets, Accelerate, and other optional packages like CUDA and Deepspeed. The tool facilitates environment setup, data preparation, data preprocessing, model downloading, parameter configuration, model fine-tuning, and inference through a browser demo or API service. Additionally, it offers the ability to deploy a WeChat chatbot, although users should be cautious due to the risk of account suspension by WeChat.

An AI Chatbot framework built in Python. It allows users to easily create Natural Language conversational scenarios with no coding efforts. The tool continuously learns from conversations to improve its capabilities. It can be integrated with various channels like Messenger and Slack. Users can create AI-powered chatbots without expertise in artificial intelligence.

Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.