MathVerse is an all-around visual math benchmark designed to evaluate the capabilities of Multi-modal Large Language Models (MLLMs) in visual math problem-solving. It collects high-quality math problems with diagrams to assess how well MLLMs can understand visual diagrams for mathematical reasoning. The benchmark includes 2,612 problems transformed into six versions each, contributing to 15K test samples. It also introduces a Chain-of-Thought (CoT) Evaluation strategy for fine-grained assessment of output answers.

OpenCompass is a one-stop platform for large model evaluation, aiming to provide a fair, open, and reproducible benchmark for large model evaluation. Its main features include: * Comprehensive support for models and datasets: Pre-support for 20+ HuggingFace and API models, a model evaluation scheme of 70+ datasets with about 400,000 questions, comprehensively evaluating the capabilities of the models in five dimensions. * Efficient distributed evaluation: One line command to implement task division and distributed evaluation, completing the full evaluation of billion-scale models in just a few hours. * Diversified evaluation paradigms: Support for zero-shot, few-shot, and chain-of-thought evaluations, combined with standard or dialogue-type prompt templates, to easily stimulate the maximum performance of various models. * Modular design with high extensibility: Want to add new models or datasets, customize an advanced task division strategy, or even support a new cluster management system? Everything about OpenCompass can be easily expanded! * Experiment management and reporting mechanism: Use config files to fully record each experiment, and support real-time reporting of results.

Video-MME is the first-ever comprehensive evaluation benchmark of Multi-modal Large Language Models (MLLMs) in Video Analysis. It assesses the capabilities of MLLMs in processing video data, covering a wide range of visual domains, temporal durations, and data modalities. The dataset comprises 900 videos with 256 hours and 2,700 human-annotated question-answer pairs. It distinguishes itself through features like duration variety, diversity in video types, breadth in data modalities, and quality in annotations.

VITA is an open-source interactive omni multimodal Large Language Model (LLM) capable of processing video, image, text, and audio inputs simultaneously. It stands out with features like Omni Multimodal Understanding, Non-awakening Interaction, and Audio Interrupt Interaction. VITA can respond to user queries without a wake-up word, track and filter external queries in real-time, and handle various query inputs effectively. The model utilizes state tokens and a duplex scheme to enhance the multimodal interactive experience.

FireRedTTS is a foundation text-to-speech framework designed for industry-level generative speech applications. It offers a rich-punctuation model with expanded punctuation coverage and enhanced audio production consistency. The tool provides pre-trained checkpoints, inference code, and an interactive demo space. Users can clone the repository, create a conda environment, download required model files, and utilize the tool for synthesizing speech in various languages. FireRedTTS aims to enhance stability and provide controllable human-like speech generation capabilities.

FastAgency is a powerful tool that leverages the AutoGen framework to quickly build applications with multi-agent workflows. It supports various interfaces like ConsoleUI and MesopUI, allowing users to create interactive applications. The tool enables defining workflows between agents, such as students and teachers, and summarizing conversations. FastAgency aims to expand its capabilities by integrating with additional agentic frameworks like CrewAI, providing more options for workflow definition and AI tool integration.

GPT4Point is a unified framework for point-language understanding and generation. It aligns 3D point clouds with language, providing a comprehensive solution for tasks such as 3D captioning and controlled 3D generation. The project includes an automated point-language dataset annotation engine, a novel object-level point cloud benchmark, and a 3D multi-modality model. Users can train and evaluate models using the provided code and datasets, with a focus on improving models' understanding capabilities and facilitating the generation of 3D objects.

TaskingAI brings Firebase's simplicity to **AI-native app development**. The platform enables the creation of GPTs-like multi-tenant applications using a wide range of LLMs from various providers. It features distinct, modular functions such as Inference, Retrieval, Assistant, and Tool, seamlessly integrated to enhance the development process. TaskingAI’s cohesive design ensures an efficient, intelligent, and user-friendly experience in AI application development.

Holistic AI is an open-source library dedicated to assessing and improving the trustworthiness of AI systems. It focuses on measuring and mitigating bias, explainability, robustness, security, and efficacy in AI models. The tool provides comprehensive metrics, mitigation techniques, a user-friendly interface, and visualization tools to enhance AI system trustworthiness. It offers documentation, tutorials, and detailed installation instructions for easy integration into existing workflows.

MMStar is an elite vision-indispensable multi-modal benchmark comprising 1,500 challenge samples meticulously selected by humans. It addresses two key issues in current LLM evaluation: the unnecessary use of visual content in many samples and the existence of unintentional data leakage in LLM and LVLM training. MMStar evaluates 6 core capabilities across 18 detailed axes, ensuring a balanced distribution of samples across all dimensions.

Edgen is a local GenAI API server that serves as a drop-in replacement for OpenAI's API. It provides multi-endpoint support for chat completions and speech-to-text, is model agnostic, offers optimized inference, and features model caching. Built in Rust, Edgen is natively compiled for Windows, MacOS, and Linux, eliminating the need for Docker. It allows users to utilize GenAI locally on their devices for free and with data privacy. With features like session caching, GPU support, and support for various endpoints, Edgen offers a scalable, reliable, and cost-effective solution for running GenAI applications locally.

llmc is an off-the-shell tool designed for compressing LLM, leveraging state-of-the-art compression algorithms to enhance efficiency and reduce model size without compromising performance. It provides users with the ability to quantize LLMs, choose from various compression algorithms, export transformed models for further optimization, and directly infer compressed models with a shallow memory footprint. The tool supports a range of model types and quantization algorithms, with ongoing development to include pruning techniques. Users can design their configurations for quantization and evaluation, with documentation and examples planned for future updates. llmc is a valuable resource for researchers working on post-training quantization of large language models.

InternGPT (iGPT) is a pointing-language-driven visual interactive system that enhances communication between users and chatbots by incorporating pointing instructions. It improves chatbot accuracy in vision-centric tasks, especially in complex visual scenarios. The system includes an auxiliary control mechanism to enhance the control capability of the language model. InternGPT features a large vision-language model called Husky, fine-tuned for high-quality multi-modal dialogue. Users can interact with ChatGPT by clicking, dragging, and drawing using a pointing device, leading to efficient communication and improved chatbot performance in vision-related tasks.

AirSLAM is an efficient visual SLAM system designed to tackle short-term and long-term illumination challenges. It combines deep learning techniques with traditional optimization methods, featuring a unified CNN for keypoint and structural line extraction. The system includes a relocalization pipeline for map reuse, accelerated using C++ and NVIDIA TensorRT. Outperforming other SLAM systems in challenging environments, it runs at 73Hz on PC and 40Hz on embedded platforms.

BetterGI is a project based on computer vision technology, which aims to make Genshin Impact better. It can automatically pick up items, skip dialogues, automatically select options, automatically submit items, close pop-up pages, etc. When talking to Katherine, it can automatically receive the "Daily Commission" rewards and automatically re-dispatch. When the automatic plot function is turned on, this function will take effect, and the invitation options will be automatically selected. AI recognizes automatic casting, automatically reels in when the fish is hooked, and automatically completes the fishing progress. Help you easily complete the Seven Saint Summoning character invitation, weekly visitor challenge and other PVE content. Automatically use the "King Tree Blessing" with the `Z` key, and use the principle of refreshing wood by going online and offline to hang up a backpack full of wood. Write combat scripts to let the team fight automatically according to your strategy. Fully automatic secret realm hangs up to restore physical strength, automatically enters the secret realm to open the key, fight, walk to the ancient tree and receive rewards. Click the teleportation point on the map, or if there is a teleportation point in the list that appears after clicking, it will automatically click the teleportation point and teleport. Set a shortcut key, and long press to continuously rotate the perspective horizontally (of course you can also use it to rotate the grass god). Quickly switch between "Details" and "Enhance" pages to skip the display of holy relic enhancement results and quickly +20. You can quickly purchase items in the store in full quantity, which is suitable for quickly clearing event redemptions,塵歌壺 store redemptions, etc.

Mercury is a code efficiency benchmark designed for code synthesis tasks. It includes 1,889 programming tasks of varying difficulty levels and provides test case generators for comprehensive evaluation. The benchmark aims to assess the efficiency of large language models in generating code solutions.

MathVerse is an all-around visual math benchmark designed to evaluate the capabilities of Multi-modal Large Language Models (MLLMs) in visual math problem-solving. It collects high-quality math problems with diagrams to assess how well MLLMs can understand visual diagrams for mathematical reasoning. The benchmark includes 2,612 problems transformed into six versions each, contributing to 15K test samples. It also introduces a Chain-of-Thought (CoT) Evaluation strategy for fine-grained assessment of output answers.

Video-MME is the first-ever comprehensive evaluation benchmark of Multi-modal Large Language Models (MLLMs) in Video Analysis. It assesses the capabilities of MLLMs in processing video data, covering a wide range of visual domains, temporal durations, and data modalities. The dataset comprises 900 videos with 256 hours and 2,700 human-annotated question-answer pairs. It distinguishes itself through features like duration variety, diversity in video types, breadth in data modalities, and quality in annotations.

MiniCPM is a series of open-source large models on the client side jointly developed by Face Intelligence and Tsinghua University Natural Language Processing Laboratory. The main language model MiniCPM-2B has only 2.4 billion (2.4B) non-word embedding parameters, with a total of 2.7B parameters. - After SFT, MiniCPM-2B performs similarly to Mistral-7B on public comprehensive evaluation sets (better in Chinese, mathematics, and code capabilities), and outperforms models such as Llama2-13B, MPT-30B, and Falcon-40B overall. - After DPO, MiniCPM-2B also surpasses many representative open-source large models such as Llama2-70B-Chat, Vicuna-33B, Mistral-7B-Instruct-v0.1, and Zephyr-7B-alpha on the current evaluation set MTBench, which is closest to the user experience. - Based on MiniCPM-2B, a multi-modal large model MiniCPM-V 2.0 on the client side is constructed, which achieves the best performance of models below 7B in multiple test benchmarks, and surpasses larger parameter scale models such as Qwen-VL-Chat 9.6B, CogVLM-Chat 17.4B, and Yi-VL 34B on the OpenCompass leaderboard. MiniCPM-V 2.0 also demonstrates leading OCR capabilities, approaching Gemini Pro in scene text recognition capabilities. - After Int4 quantization, MiniCPM can be deployed and inferred on mobile phones, with a streaming output speed slightly higher than human speech speed. MiniCPM-V also directly runs through the deployment of multi-modal large models on mobile phones. - A single 1080/2080 can efficiently fine-tune parameters, and a single 3090/4090 can fully fine-tune parameters. A single machine can continuously train MiniCPM, and the secondary development cost is relatively low.

This repository contains an assistant proposal for the Semantic Kernel, allowing the usage of assistants without relying on OpenAI Assistant APIs. It runs locally planners and plugins for the assistants, providing scenarios like Assistant with Semantic Kernel plugins, Multi-Assistant conversation, and AutoGen conversation. The Semantic Kernel is a lightweight SDK enabling integration of AI Large Language Models with conventional programming languages, offering functions like semantic functions, native functions, and embeddings-based memory. Users can bring their own model for the assistants and host them locally. The repository includes installation instructions, usage examples, and information on creating new conversation threads with the assistant.

AMchat is a large language model that integrates advanced math concepts, exercises, and solutions. The model is based on the InternLM2-Math-7B model and is specifically designed to answer advanced math problems. It provides a comprehensive dataset that combines Math and advanced math exercises and solutions. Users can download the model from ModelScope or OpenXLab, deploy it locally or using Docker, and even retrain it using XTuner for fine-tuning. The tool also supports LMDeploy for quantization, OpenCompass for evaluation, and various other features for model deployment and evaluation. The project contributors have provided detailed documentation and guides for users to utilize the tool effectively.

The Self-Iterative Agent System for Complex Problem Solving is a solution developed for the Alibaba Mathematical Competition (AI Challenge). It involves multiple LLMs engaging in multi-round 'self-questioning' to iteratively refine the problem-solving process and select optimal solutions. The system consists of main and evaluation models, with a process that includes detailed problem-solving steps, feedback loops, and iterative improvements. The approach emphasizes communication and reasoning between sub-agents, knowledge extraction, and the importance of Agent-like architectures in complex tasks. While effective, there is room for improvement in model capabilities and error prevention mechanisms.

LLM4Opt is a collection of references and papers focusing on applying Large Language Models (LLMs) for diverse optimization tasks. The repository includes research papers, tutorials, workshops, competitions, and related collections related to LLMs in optimization. It covers a wide range of topics such as algorithm search, code generation, machine learning, science, industry, and more. The goal is to provide a comprehensive resource for researchers and practitioners interested in leveraging LLMs for optimization tasks.

Awesome LLM Strawberry is a collection of research papers and blogs related to OpenAI Strawberry(o1) and Reasoning. The repository is continuously updated to track the frontier of LLM Reasoning.

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.