3 个仓库
Awesome GitHub RepositoriesInstructional Input Optimizers
Tools that structure instructions and retrieved knowledge to provide models with the most relevant data for specific tasks.
Distinct from Model Performance Optimization: Distinct from general model performance optimization: focuses on the structuring of input prompts and context rather than model-level quantization.
Explore 3 awesome GitHub repositories matching artificial intelligence & ml · Instructional Input Optimizers. Refine with filters or upvote what's useful.
Awesome Instructional Input Optimizers GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- datawhalechina/hello-agents
datawhalechina/hello-agents
59,685在 GitHub 上查看This project provides a comprehensive framework for building, training, and managing autonomous agents. It enables the construction of systems that utilize language models to plan, manage memory, and execute multi-step tasks through iterative reasoning loops and tool-based actions. The framework distinguishes itself by offering specialized capabilities for interacting with graphical user interfaces and legacy software, allowing agents to perceive visual elements and perform actions like a human user. It supports complex, cross-application workflows through graph-based orchestration and provid
Structures instructions and retrieved knowledge to provide models with the most relevant data needed to complete tasks accurately.
Pythonagentllmrag - dask/dask
dask/dask
13,746在 GitHub 上查看Dask 是一个并行计算框架和分布式任务调度器，旨在将 Python 数据科学工作流从单机扩展到大型集群。它作为一个集群资源管理器，通过将任务及其依赖项表示为有向无环图来编排计算逻辑。这种架构允许系统在管理复杂执行要求的同时，自动将工作负载分配到可用硬件上。 该项目通过一个延迟评估引擎脱颖而出，该引擎将数据操作推迟到明确请求时才执行，从而实现全局图优化和高效的资源分配。它结合了内存感知数据溢出功能，以防止在处理超过可用内存的数据集时系统崩溃，并利用任务图融合将操作序列组合成单个执行步骤，从而最大限度地减少调度开销和节点间通信。 该平台为大规模数据分析提供了全面的功能面，包括对分布式机器学习、高性能计算集成和并行数据处理的支持。它提供了用于集群生命周期管理、性能分析和任务执行实时监控的广泛工具。用户可以在各种基础设施上部署这些环境，包括本地硬件、云提供商、容器化系统和高性能计算集群。
Delays large data inputs to prevent redundant hashing and excessive memory usage during distributed processing.
Pythondasknumpypandas - boundaryml/baml
BoundaryML/baml
7,636在 GitHub 上查看BAML is a prompt engineering framework and LLM client generator that defines AI prompts as type-safe functions. It serves as a structured data extraction tool and workflow orchestrator, transforming unstructured model responses into strongly typed objects using a custom schema language and alignment algorithms. The project distinguishes itself by using a compiler to generate language-specific boilerplate code for API communication and output parsing. It features a dedicated environment for designing complex prompt templates with conditional logic and reusable snippets, and employs genetic alg
Reduces token count by pruning data or splitting prompts to minimize model confusion and hallucinations.
Rustbamlboundarymlguardrails
