ms-swift is an official framework provided by the ModelScope community for fine-tuning and deploying large language models and multi-modal large models. It supports training, inference, evaluation, quantization, and deployment of over 400 large models and 100+ multi-modal large models. The framework includes various training technologies and accelerates inference, evaluation, and deployment modules. It offers a Gradio-based Web-UI interface and best practices for easy application of large models. ms-swift supports a wide range of model types, dataset types, hardware support, lightweight training methods, distributed training techniques, quantization training, RLHF training, multi-modal training, interface training, plugin and extension support, inference acceleration engines, model evaluation, and model quantization.

SWIFT (Scalable lightWeight Infrastructure for Fine-Tuning) supports training, inference, evaluation and deployment of nearly **200 LLMs and MLLMs** (multimodal large models). Developers can directly apply our framework to their own research and production environments to realize the complete workflow from model training and evaluation to application. In addition to supporting the lightweight training solutions provided by [PEFT](https://github.com/huggingface/peft), we also provide a complete **Adapters library** to support the latest training techniques such as NEFTune, LoRA+, LLaMA-PRO, etc. This adapter library can be used directly in your own custom workflow without our training scripts. To facilitate use by users unfamiliar with deep learning, we provide a Gradio web-ui for controlling training and inference, as well as accompanying deep learning courses and best practices for beginners. Additionally, we are expanding capabilities for other modalities. Currently, we support full-parameter training and LoRA training for AnimateDiff.

NVIDIA BioNeMo Framework is a collection of programming tools, libraries, and models for computational drug discovery. It accelerates building and adapting biomolecular AI models by providing domain-specific, optimized models and tooling for GPU-based computational resources. The framework offers comprehensive documentation and support for both community and enterprise users.

Astra.ai is a multimodal agent powered by TEN, showcasing its capabilities in speech, vision, and reasoning through RAG from local documentation. It provides a platform for developing AI agents with features like RTC transportation, extension store, workflow builder, and local deployment. Users can build and test agents locally using Docker and Node.js, with prerequisites including Agora App ID, Azure's speech-to-text and text-to-speech API keys, and OpenAI API key. The platform offers advanced customization options through config files and API keys setup, enabling users to create and deploy their AI agents for various tasks.

Helicone is an open-source observability platform designed for Language Learning Models (LLMs). It logs requests to OpenAI in a user-friendly UI, offers caching, rate limits, and retries, tracks costs and latencies, provides a playground for iterating on prompts and chat conversations, supports collaboration, and will soon have APIs for feedback and evaluation. The platform is deployed on Cloudflare and consists of services like Web (NextJs), Worker (Cloudflare Workers), Jawn (Express), Supabase, and ClickHouse. Users can interact with Helicone locally by setting up the required services and environment variables. The platform encourages contributions and provides resources for learning, documentation, and integrations.

New API is a next-generation large model gateway and AI asset management system that provides a wide range of features, including a new UI interface, multi-language support, online recharge function, key query for usage quota, compatibility with the original One API database, model charging by usage count, channel weighted randomization, data dashboard, token grouping and model restrictions, support for various authorization login methods, support for Rerank models, OpenAI Realtime API, Claude Messages format, reasoning effort setting, content reasoning, user-specific model rate limiting, request format conversion, cache billing support, and various model support such as gpts, Midjourney-Proxy, Suno API, custom channels, Rerank models, Claude Messages format, Dify, and more.

Llumen is a self-hosted interface optimized for modest hardware like Raspberry Pi, old laptops, and minimal VPS. It offers privacy without complexity, providing essential features with minimal resource demands. Users can enjoy sub-second cold starts, real-time token streaming, various chat modes, rich media support, and a universal API for OpenAI-compatible providers. The tool has a small footprint with a binary size of around 17MB and RAM usage under 128MB. Llumen aims to simplify the setup process and offer a user-friendly experience for individuals seeking a privacy-focused solution.

PR-Agent is a tool designed to assist in efficiently reviewing and handling pull requests by providing AI feedback and suggestions. It offers various tools such as Review, Describe, Improve, Ask, Update CHANGELOG, and more, with the ability to run them via different interfaces like CLI, PR Comments, or automatically triggering them when a new PR is opened. The tool supports multiple git platforms and models, emphasizing real-life practical usage and modular, customizable tools.

Composio is a production-ready toolset for AI agents that enables users to integrate AI agents with various agentic tools effortlessly. It provides support for over 100 tools across different categories, including popular softwares like GitHub, Notion, Linear, Gmail, Slack, and more. Composio ensures managed authorization with support for six different authentication protocols, offering better agentic accuracy and ease of use. Users can easily extend Composio with additional tools, frameworks, and authorization protocols. The toolset is designed to be embeddable and pluggable, allowing for seamless integration and consistent user experience.

ASTRA is an open-source platform designed for developing applications utilizing large language models. It merges the ideas of Backend-as-a-Service and LLM operations, allowing developers to swiftly create production-ready generative AI applications. Additionally, it empowers non-technical users to engage in defining and managing data operations for AI applications. With ASTRA, you can easily create real-time, multi-modal AI applications with low latency, even without any coding knowledge.

InternLM is a powerful language model series with features such as 200K context window for long-context tasks, outstanding comprehensive performance in reasoning, math, code, chat experience, instruction following, and creative writing, code interpreter & data analysis capabilities, and stronger tool utilization capabilities. It offers models in sizes of 7B and 20B, suitable for research and complex scenarios. The models are recommended for various applications and exhibit better performance than previous generations. InternLM models may match or surpass other open-source models like ChatGPT. The tool has been evaluated on various datasets and has shown superior performance in multiple tasks. It requires Python >= 3.8, PyTorch >= 1.12.0, and Transformers >= 4.34 for usage. InternLM can be used for tasks like chat, agent applications, fine-tuning, deployment, and long-context inference.

FalkorDB is the first queryable Property Graph database to use sparse matrices to represent the adjacency matrix in graphs and linear algebra to query the graph. Primary features: * Adopting the Property Graph Model * Nodes (vertices) and Relationships (edges) that may have attributes * Nodes can have multiple labels * Relationships have a relationship type * Graphs represented as sparse adjacency matrices * OpenCypher with proprietary extensions as a query language * Queries are translated into linear algebra expressions

hCaptcha Challenger is a tool designed to gracefully face hCaptcha challenges using a multimodal large language model. It does not rely on Tampermonkey scripts or third-party anti-captcha services, instead implementing interfaces for 'AI vs AI' scenarios. The tool supports various challenge types such as image labeling, drag and drop, and advanced tasks like self-supervised challenges and Agentic Workflow. Users can access documentation in multiple languages and leverage resources for tasks like model training, dataset annotation, and model upgrading. The tool aims to enhance user experience in handling hCaptcha challenges with innovative AI capabilities.

Uni-MoE is a MoE-based unified multimodal model that can handle diverse modalities including audio, speech, image, text, and video. The project focuses on scaling Unified Multimodal LLMs with a Mixture of Experts framework. It offers enhanced functionality for training across multiple nodes and GPUs, as well as parallel processing at both the expert and modality levels. The model architecture involves three training stages: building connectors for multimodal understanding, developing modality-specific experts, and incorporating multiple trained experts into LLMs using the LoRA technique on mixed multimodal data. The tool provides instructions for installation, weights organization, inference, training, and evaluation on various datasets.

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.

EVE is an official PyTorch implementation of Unveiling Encoder-Free Vision-Language Models. The project aims to explore the removal of vision encoders from Vision-Language Models (VLMs) and transfer LLMs to encoder-free VLMs efficiently. It also focuses on bridging the performance gap between encoder-free and encoder-based VLMs. EVE offers a superior capability with arbitrary image aspect ratio, data efficiency by utilizing publicly available data for pre-training, and training efficiency with a transparent and practical strategy for developing a pure decoder-only architecture across modalities.

AutoGPTQ is an easy-to-use LLM quantization package with user-friendly APIs, based on GPTQ algorithm (weight-only quantization). It provides a simple and efficient way to quantize large language models (LLMs) to reduce their size and computational cost while maintaining their performance. AutoGPTQ supports a wide range of LLM models, including GPT-2, GPT-J, OPT, and BLOOM. It also supports various evaluation tasks, such as language modeling, sequence classification, and text summarization. With AutoGPTQ, users can easily quantize their LLM models and deploy them on resource-constrained devices, such as mobile phones and embedded systems.

Qwen-TensorRT-LLM is a project developed for the NVIDIA TensorRT Hackathon 2023, focusing on accelerating inference for the Qwen-7B-Chat model using TRT-LLM. The project offers various functionalities such as FP16/BF16 support, INT8 and INT4 quantization options, Tensor Parallel for multi-GPU parallelism, web demo setup with gradio, Triton API deployment for maximum throughput/concurrency, fastapi integration for openai requests, CLI interaction, and langchain support. It supports models like qwen2, qwen, and qwen-vl for both base and chat models. The project also provides tutorials on Bilibili and blogs for adapting Qwen models in NVIDIA TensorRT-LLM, along with hardware requirements and quick start guides for different model types and quantization methods.

The stable-diffusion.cpp repository provides an implementation for inferring stable diffusion in pure C/C++. It offers features such as support for different versions of stable diffusion, lightweight and dependency-free implementation, various quantization support, memory-efficient CPU inference, GPU acceleration, and more. Users can download the built executable program or build it manually. The repository also includes instructions for downloading weights, building from scratch, using different acceleration methods, running the tool, converting weights, and utilizing various features like Flash Attention, ESRGAN upscaling, PhotoMaker support, and more. Additionally, it mentions future TODOs and provides information on memory requirements, bindings, UIs, contributors, and references.

LMOps is a research initiative focusing on fundamental research and technology for building AI products with foundation models, particularly enabling AI capabilities with Large Language Models (LLMs) and Generative AI models. The project explores various aspects such as prompt optimization, longer context handling, LLM alignment, acceleration of LLMs, LLM customization, and understanding in-context learning. It also includes tools like Promptist for automatic prompt optimization, Structured Prompting for efficient long-sequence prompts consumption, and X-Prompt for extensible prompts beyond natural language. Additionally, LLMA accelerators are developed to speed up LLM inference by referencing and copying text spans from documents. The project aims to advance technologies that facilitate prompting language models and enhance the performance of LLMs in various scenarios.

Awesome-Efficient-LLM is a curated list focusing on efficient large language models. It includes topics such as knowledge distillation, network pruning, quantization, inference acceleration, efficient MOE, efficient architecture of LLM, KV cache compression, text compression, low-rank decomposition, hardware/system, tuning, and survey. The repository provides a collection of papers and projects related to improving the efficiency of large language models through various techniques like sparsity, quantization, and compression.

The NVIDIA TensorRT Model Optimizer is a library designed to quantize and compress deep learning models for optimized inference on GPUs. It offers state-of-the-art model optimization techniques including quantization and sparsity to reduce inference costs for generative AI models. Users can easily stack different optimization techniques to produce quantized checkpoints from torch or ONNX models. The quantized checkpoints are ready for deployment in inference frameworks like TensorRT-LLM or TensorRT, with planned integrations for NVIDIA NeMo and Megatron-LM. The tool also supports 8-bit quantization with Stable Diffusion for enterprise users on NVIDIA NIM. Model Optimizer is available for free on NVIDIA PyPI, and this repository serves as a platform for sharing examples, GPU-optimized recipes, and collecting community feedback.

Bolts package provides a variety of components to extend PyTorch Lightning, such as callbacks & datasets, for applied research and production. Users can accelerate Lightning training with the Torch ORT Callback to optimize ONNX graph for faster training & inference. Additionally, users can introduce sparsity with the SparseMLCallback to accelerate inference by leveraging the DeepSparse engine. Specific research implementations are encouraged, with contributions that help train SSL models and integrate with Lightning Flash for state-of-the-art models in applied research.

ms-swift is an official framework provided by the ModelScope community for fine-tuning and deploying large language models and multi-modal large models. It supports training, inference, evaluation, quantization, and deployment of over 400 large models and 100+ multi-modal large models. The framework includes various training technologies and accelerates inference, evaluation, and deployment modules. It offers a Gradio-based Web-UI interface and best practices for easy application of large models. ms-swift supports a wide range of model types, dataset types, hardware support, lightweight training methods, distributed training techniques, quantization training, RLHF training, multi-modal training, interface training, plugin and extension support, inference acceleration engines, model evaluation, and model quantization.

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.