Search Results for "records"

OpenDAN is an open-source Personal AI OS , that consolidates various AI modules in one place for your personal use. The goal of OpenDAN (Open and Do Anything Now with AI) is to create a Personal AI OS , which provides a runtime environment for various Al modules as well as protocols for interoperability between them. With OpenDAN, users can securely collaborate with various AI modules using their private data to create powerful personal AI agents, such as butlers, lawyers, doctors, teachers,...

...The system allows developers to define specific scenarios, expected outcomes, and business rules so that the framework can verify whether an agent behaves according to required policies. During testing, Rogue records conversations and produces detailed reports that explain whether the agent passed or failed each scenario. These reports include reasoning and evidence, helping developers understand why a particular failure occurred.

SwanLab is an open-source experiment tracking and visualization platform designed to help machine learning engineers monitor, compare, and analyze the training of artificial intelligence models. The tool records training metrics, hyperparameters, model outputs, and experiment configurations so that developers can easily understand how different experiments perform over time. It provides a modern user interface for visualizing results, enabling teams to compare runs, track model performance trends, and collaborate on machine learning research. ...

...The project focuses on developing domain-specific language models that understand financial terminology, corporate reports, and economic datasets. By combining large language model architectures with financial datasets such as corporate annual reports and structured financial records, FinGLM aims to improve AI performance on tasks that require domain expertise. The repository also provides educational materials and tutorials that help developers learn how to build and fine-tune financial AI systems using the GLM model ecosystem. In addition to model development, the project promotes collaboration between researchers, companies, and developers interested in applying AI to financial analysis.

...The project was developed to address concerns that AI-assisted programming tools may produce insecure code containing vulnerabilities such as injection flaws or unsafe logic. The framework constructs evaluation tasks based on real-world software repositories and known vulnerability cases derived from CVE records. By simulating realistic development scenarios, the benchmark assesses how well AI code generation systems handle security-sensitive programming tasks. AICGSecEval combines static and dynamic evaluation techniques to analyze generated code for vulnerabilities and functional correctness. The framework includes datasets, test cases, and evaluation metrics that measure how AI programming tools perform across multiple programming languages and vulnerability categories.

...In this framework, each node in the pipeline represents a step in the reasoning or action process, while prompts and tools act as adjustable parameters analogous to neural network weights. During training, the system performs a forward execution where the agent completes a task and records the trajectory of prompts, outputs, and tool usage. A prompt-based loss function is then applied to evaluate the quality of the outcome, generating language-based gradients that guide improvements to the agent pipeline.

This repository records EleutherAI's library for training large-scale language models on GPUs. Our current framework is based on NVIDIA's Megatron Language Model and has been augmented with techniques from DeepSpeed as well as some novel optimizations. We aim to make this repo a centralized and accessible place to gather techniques for training large-scale autoregressive language models, and accelerate research into large-scale training.