Best AI tools for< Reproduce Experiments >

Sacred is a tool to configure, organize, log and reproduce computational experiments. It is designed to introduce only minimal overhead, while encouraging modularity and configurability of experiments. The ability to conveniently make experiments configurable is at the heart of Sacred. If the parameters of an experiment are exposed in this way, it will help you to: keep track of all the parameters of your experiment easily run your experiment for different settings save configurations for individual runs in files or a database reproduce your results In Sacred we achieve this through the following main mechanisms: Config Scopes are functions with a @ex.config decorator, that turn all local variables into configuration entries. This helps to set up your configuration really easily. Those entries can then be used in captured functions via dependency injection. That way the system takes care of passing parameters around for you, which makes using your config values really easy. The command-line interface can be used to change the parameters, which makes it really easy to run your experiment with modified parameters. Observers log every information about your experiment and the configuration you used, and saves them for example to a Database. This helps to keep track of all your experiments. Automatic seeding helps controlling the randomness in your experiments, such that they stay reproducible.

Comet ML is a machine learning platform that integrates with your existing infrastructure and tools so you can manage, visualize, and optimize models—from training runs to production monitoring.

Comet ML is a machine learning platform that integrates with your existing infrastructure and tools so you can manage, visualize, and optimize models—from training runs to production monitoring.

Comet ML is an extensible, fully customizable machine learning platform that aims to move ML forward by supporting productivity, reproducibility, and collaboration. It integrates with existing infrastructure and tools to manage, visualize, and optimize models from training runs to production monitoring. Users can track and compare training runs, create a model registry, and monitor models in production all in one platform. Comet's platform can be run on any infrastructure, enabling users to reshape their ML workflow and bring their existing software and data stack.

Jam is a bug-tracking tool that helps developers reproduce and debug issues quickly and easily. It automatically captures all the information engineers need to debug, including device and browser information, console logs, network logs, repro steps, and backend tracing. Jam also integrates with popular tools like GitHub, Jira, Linear, Slack, ClickUp, Asana, Sentry, Figma, Datadog, Gitlab, Notion, and Airtable. With Jam, developers can save time and effort by eliminating the need to write repro steps and manually collect information. Jam is used by over 90,000 developers and has received over 150 positive reviews.

MonsterImage.AI is an AI-powered tool that allows users to create cool pattern images using Artificial Intelligence. Users can input prompts to describe the image they want to create, select patterns, specify what they don't want to see in the image, use seeds for reproduction, and adjust guidance scale for classifier-free guidance. The tool provides advanced options like controlnet conditioning scale and inference steps to enhance image creation. Users can create images publicly or save them in their collection.

Union.ai is an infrastructure platform designed for AI, ML, and data workloads. It offers a scalable MLOps platform that optimizes resources, reduces costs, and fosters collaboration among team members. Union.ai provides features such as declarative infrastructure, data lineage tracking, accelerated datasets, and more to streamline AI orchestration on Kubernetes. It aims to simplify the management of AI, ML, and data workflows in production environments by addressing complexities and offering cost-effective strategies.

ForgeFluencer is an AI application that serves as an essential toolkit for crafting AI influencers and generating consistent and compelling content. It offers a user-friendly platform optimized for desktop and mobile, allowing users to create models, control various aspects of content generation, edit images with AI, and more. With features like Virtual Wardrobe, Pose Controller, and Photo Studio, ForgeFluencer empowers users to elevate their projects with AI-generated content effortlessly.

FabFab is an AI-powered platform that offers unique, one-of-a-kind t-shirts designed by artificial intelligence. The platform combines art, technology, and individuality to create personalized wearable art pieces. Each shirt is part of the broader FabFab art project, aiming to harmoniously blend human expression with AI creativity. FabFab provides a canvas for the unconventional, allowing users to choose their shirt size and have a singular design crafted just for them. The platform partners with top-notch manufacturers to ensure high-quality materials and craftsmanship. By joining FabFab, users become part of a collective movement that celebrates creativity, uniqueness, and the evolving relationship between humans and AI.

ChatAFL is a protocol fuzzer guided by large language models (LLMs) that extracts machine-readable grammar for protocol mutation, increases message diversity, and breaks coverage plateaus. It integrates with ProfuzzBench for stateful fuzzing of network protocols, providing smooth integration. The artifact includes modified versions of AFLNet and ProfuzzBench, source code for ChatAFL with proposed strategies, and scripts for setup, execution, analysis, and cleanup. Users can analyze data, construct plots, examine LLM-generated grammars, enriched seeds, and state-stall responses, and reproduce results with downsized experiments. Customization options include modifying fuzzers, tuning parameters, adding new subjects, troubleshooting, and working on GPT-4. Limitations include interaction with OpenAI's Large Language Models and a hard limit of 150,000 tokens per minute.

ReproModel is an open-source toolbox designed to boost AI research efficiency by enabling researchers to reproduce, compare, train, and test AI models faster. It provides standardized models, dataloaders, and processing procedures, allowing researchers to focus on new datasets and model development. With a no-code solution, users can access benchmark and SOTA models and datasets, utilize training visualizations, extract code for publication, and leverage an LLM-powered automated methodology description writer. The toolbox helps researchers modularize development, compare pipeline performance reproducibly, and reduce time for model development, computation, and writing. Future versions aim to facilitate building upon state-of-the-art research by loading previously published study IDs with verified code, experiments, and results stored in the system.

Collective Mind (CM) is a collection of portable, extensible, technology-agnostic and ready-to-use automation recipes with a human-friendly interface (aka CM scripts) to unify and automate all the manual steps required to compose, run, benchmark and optimize complex ML/AI applications on any platform with any software and hardware: see online catalog and source code. CM scripts require Python 3.7+ with minimal dependencies and are continuously extended by the community and MLCommons members to run natively on Ubuntu, MacOS, Windows, RHEL, Debian, Amazon Linux and any other operating system, in a cloud or inside automatically generated containers while keeping backward compatibility - please don't hesitate to report encountered issues here and contact us via public Discord Server to help this collaborative engineering effort! CM scripts were originally developed based on the following requirements from the MLCommons members to help them automatically compose and optimize complex MLPerf benchmarks, applications and systems across diverse and continuously changing models, data sets, software and hardware from Nvidia, Intel, AMD, Google, Qualcomm, Amazon and other vendors: * must work out of the box with the default options and without the need to edit some paths, environment variables and configuration files; * must be non-intrusive, easy to debug and must reuse existing user scripts and automation tools (such as cmake, make, ML workflows, python poetry and containers) rather than substituting them; * must have a very simple and human-friendly command line with a Python API and minimal dependencies; * must require minimal or zero learning curve by using plain Python, native scripts, environment variables and simple JSON/YAML descriptions instead of inventing new workflow languages; * must have the same interface to run all automations natively, in a cloud or inside containers. CM scripts were successfully validated by MLCommons to modularize MLPerf inference benchmarks and help the community automate more than 95% of all performance and power submissions in the v3.1 round across more than 120 system configurations (models, frameworks, hardware) while reducing development and maintenance costs.

Bonito is an open-source model for conditional task generation, converting unannotated text into task-specific training datasets for instruction tuning. It is a lightweight library built on top of Hugging Face `transformers` and `vllm` libraries. The tool supports various task types such as question answering, paraphrase generation, sentiment analysis, summarization, and more. Users can easily generate synthetic instruction tuning datasets using Bonito for zero-shot task adaptation.

Awesome MLOps is a curated list of tools related to Machine Learning Operations, covering areas such as AutoML, CI/CD for Machine Learning, Data Cataloging, Data Enrichment, Data Exploration, Data Management, Data Processing, Data Validation, Data Visualization, Drift Detection, Feature Engineering, Feature Store, Hyperparameter Tuning, Knowledge Sharing, Machine Learning Platforms, Model Fairness and Privacy, Model Interpretability, Model Lifecycle, Model Serving, Model Testing & Validation, Optimization Tools, Simplification Tools, Visual Analysis and Debugging, and Workflow Tools. The repository provides a comprehensive collection of tools and resources for individuals and teams working in the field of MLOps.

HippoRAG is a novel retrieval augmented generation (RAG) framework inspired by the neurobiology of human long-term memory that enables Large Language Models (LLMs) to continuously integrate knowledge across external documents. It provides RAG systems with capabilities that usually require a costly and high-latency iterative LLM pipeline for only a fraction of the computational cost. The tool facilitates setting up retrieval corpus, indexing, and retrieval processes for LLMs, offering flexibility in choosing different online LLM APIs or offline LLM deployments through LangChain integration. Users can run retrieval on pre-defined queries or integrate directly with the HippoRAG API. The tool also supports reproducibility of experiments and provides data, baselines, and hyperparameter tuning scripts for research purposes.

This competition is organized by Javier Rando and Florian Tramèr from the ETH AI Center and SPY Lab at ETH Zurich. The goal of the competition is to create a method that can detect universal backdoors in aligned language models. A universal backdoor is a secret suffix that, when appended to any prompt, enables the model to answer harmful instructions. The competition provides a set of poisoned generation models, a reward model that measures how safe a completion is, and a dataset with prompts to run experiments. Participants are encouraged to use novel methods for red-teaming, automated approaches with low human oversight, and interpretability tools to find the trojans. The best submissions will be offered the chance to present their work at an event during the SaTML 2024 conference and may be invited to co-author a publication summarizing the competition results.

This repository contains code and results for jailbreaking leading safety-aligned LLMs with simple adaptive attacks. We show that even the most recent safety-aligned LLMs are not robust to simple adaptive jailbreaking attacks. We demonstrate how to successfully leverage access to logprobs for jailbreaking: we initially design an adversarial prompt template (sometimes adapted to the target LLM), and then we apply random search on a suffix to maximize the target logprob (e.g., of the token ``Sure''), potentially with multiple restarts. In this way, we achieve nearly 100% attack success rate---according to GPT-4 as a judge---on GPT-3.5/4, Llama-2-Chat-7B/13B/70B, Gemma-7B, and R2D2 from HarmBench that was adversarially trained against the GCG attack. We also show how to jailbreak all Claude models---that do not expose logprobs---via either a transfer or prefilling attack with 100% success rate. In addition, we show how to use random search on a restricted set of tokens for finding trojan strings in poisoned models---a task that shares many similarities with jailbreaking---which is the algorithm that brought us the first place in the SaTML'24 Trojan Detection Competition. The common theme behind these attacks is that adaptivity is crucial: different models are vulnerable to different prompting templates (e.g., R2D2 is very sensitive to in-context learning prompts), some models have unique vulnerabilities based on their APIs (e.g., prefilling for Claude), and in some settings it is crucial to restrict the token search space based on prior knowledge (e.g., for trojan detection).

Flower is a framework for building federated learning systems. It is designed to be customizable, extensible, framework-agnostic, and understandable. Flower can be used with any machine learning framework, for example, PyTorch, TensorFlow, Hugging Face Transformers, PyTorch Lightning, scikit-learn, JAX, TFLite, MONAI, fastai, MLX, XGBoost, Pandas for federated analytics, or even raw NumPy for users who enjoy computing gradients by hand.

moai is a PyTorch-based AI Model Development Kit (MDK) designed to improve data-driven model workflows, design, and understanding. It offers modularity via monads for model building blocks, reproducibility via configuration-based design, productivity via a data-driven domain modelling language (DML), extensibility via plugins, and understanding via inter-model performance and design aggregation. The tool provides specific integrated actions like play, train, evaluate, plot, diff, and reprod to support heavy data-driven workflows with analytics, knowledge extraction, and reproduction. moai relies on PyTorch, Lightning, Hydra, TorchServe, ONNX, Visdom, HiPlot, Kornia, Albumentations, and the wider open-source community for its functionalities.

DistServe improves the performance of large language models serving by disaggregating the prefill and decoding computation. It allows setting parallelism configs and scheduling strategies for the two phases independently, handling KV-Cache communication and memory management automatically. Utilizes a high-performance C++ Transformer inference library SwiftTransformer with features like model/pipeline parallelism, FlashAttention, Continuous Batching, and PagedAttention. Supports GPT-2, OPT, and LLaMA2 models.

DVC, or Data Version Control, is a command-line tool and VS Code extension that helps you develop reproducible machine learning projects. With DVC, you can version your data and models, iterate fast with lightweight pipelines, track experiments in your local Git repo, compare any data, code, parameters, model, or performance plots, and share experiments and automatically reproduce anyone's experiment.

Sarathi-Serve is the official OSDI'24 artifact submission for paper #444, focusing on 'Taming Throughput-Latency Tradeoff in LLM Inference'. It is a research prototype built on top of CUDA 12.1, designed to optimize throughput-latency tradeoff in Large Language Models (LLM) inference. The tool provides a Python environment for users to install and reproduce results from the associated experiments. Users can refer to specific folders for individual figures and are encouraged to cite the paper if they use the tool in their work.

LLMs Know More Than They Show is a repository containing code to reproduce the results in the paper. It includes scripts to generate model answers, extract exact answers, probe all layers and tokens, probe specific layers and tokens, conduct generalization experiments, perform resampling for error type probing and answer selection experiments, and run other baselines like logprob detection and p_true detection. The repository supports various datasets such as TriviaQA, Movies, HotpotQA, Winobias, Winogrande, NLI, IMDB, Math, and Natural questions. It also provides supported models like Mistral-7B-Instruct-v0.2, Mistral-7B-v0.3, Meta-Llama-3-8B, and Meta-Llama-3-8B-Instruct.

Open-Sora-Plan is a project that aims to create a simple and scalable repo to reproduce Sora (OpenAI, but we prefer to call it "ClosedAI"). The project is still in its early stages, but the team is working hard to improve it and make it more accessible to the open-source community. The project is currently focused on training an unconditional model on a landscape dataset, but the team plans to expand the scope of the project in the future to include text2video experiments, training on video2text datasets, and controlling the model with more conditions.

AgentLab is an open, easy-to-use, and extensible framework designed to accelerate web agent research. It provides features for developing and evaluating agents on various benchmarks supported by BrowserGym. The framework allows for large-scale parallel agent experiments using ray, building blocks for creating agents over BrowserGym, and a unified LLM API for OpenRouter, OpenAI, Azure, or self-hosted using TGI. AgentLab also offers reproducibility features, a unified LeaderBoard, and supports multiple benchmarks like WebArena, WorkArena, WebLinx, VisualWebArena, AssistantBench, GAIA, Mind2Web-live, and MiniWoB.

The Eureka ML Insights Framework is a repository containing code designed to help researchers and practitioners run reproducible evaluations of generative models efficiently. Users can define custom pipelines for data processing, inference, and evaluation, as well as utilize pre-defined evaluation pipelines for key benchmarks. The framework provides a structured approach to conducting experiments and analyzing model performance across various tasks and modalities.

This repository contains code for reproducing experiments on lie detection in black-box LLMs by asking unrelated questions. It includes Q/A datasets, prompts, and fine-tuning datasets for generating lies with language models. The lie detectors rely on asking binary 'elicitation questions' to diagnose whether the model has lied. The code covers generating lies from language models, training and testing lie detectors, and generalization experiments. It requires access to GPUs and OpenAI API calls for running experiments with open-source models. Results are stored in the repository for reproducibility.

Pax is a framework to configure and run machine learning experiments on top of Jax.

キーワードやコンテクストに基づいて、詳細な画像プロンプトを時間軸、文化軸、感情軸、現実と虚構軸など、多角的な視点を取り入れて、あなたのビジョンを忠実に再現します。