Results for “model architecture”

软件架构 (含 应用架构 / 系统架构 / 分布式 后端架构 / 前后端 数据流 与 数据模型 设计 / API 边界 / 可扩展性 / 演进式架构 — 不含 硬件架构 / 纯企业架构 / 纯 DevOps / 纯安全架构) (software architecture — application & system architecture for web / mobile / distributed back-ends; designing services + data models + data flow + integration boundaries; making explicit trade-offs about scalability / coupling / consistency / evolvability; not hardware / chip architecture, not pure enterprise-architecture (TOGAF/Zachman), not pure DevOps / SRE, not pure security architecture (those are adjacent disciplines).) Master OS — automated mastery of software architecture — application & system architecture for web / mobile / distributed back-ends; designing services + data models + data flow + integration boundaries; making explicit trade-offs about scalability / coupling / consistency / evolvability; not hardware / chip architecture, not pure enterprise-architecture (TOGAF/Zachman), not pure DevOps / SRE, not pure security architecture (those are adjacent disciplines).: top builders' mental models, tool stack, current workflows, jargon, and where to keep up. Trigger this skill when the user works on software architecture — application & system architecture for web / mobile / distributed back-ends; designing services + data models + data flow + integration boundaries; making explicit trade-offs about scalability / coupling / consistency / evolvability; not hardware / chip architecture, not pure enterprise-architecture (TOGAF/Zachman), not pure DevOps / SRE, not pure security architecture (those are adjacent disciplines). problems and wants industry-grade thinking, tool selection, or workflow guidance. 触发词：「软件架构」「系统设计」「system design」「应用架构」「service design」

The English summary is being prepared. Showing the original description.

Compare models available through the HuggingFace router with chat-ui configuration, research missing models, and write short English descriptions of their architecture and capabilities. Add entries to both production and development configuration files and commit the changes.

• Adding newly available router models to chat-ui
• Writing concise descriptions of model capabilities
• Updating production and development model entries together

Use LitGPT to explore language model implementations and train models on custom data. Covers pretrained model loading, LoRA fine-tuning that updates a small set of parameters, pretraining, and preparing trained models for deployment.

• Studying language model architecture through readable code
• Fine-tuning a model on custom instruction data
• Configuring LoRA training for a single GPU

Add support for a new language model in MNN, from downloading and analyzing it to mapping model fields, comparing intermediate results, and exporting files. Follow staged tests, with additional paths for image, audio, and unusual architectures.

• Adding a new text model to MNN
• Exporting a model from HuggingFace or ModelScope to MNN
• Checking intermediate outputs against the original model

Use LitGPT to explore language model implementations and train models on custom data. Covers pretrained model loading, LoRA fine-tuning that updates a small set of parameters, pretraining, and preparing trained models for deployment.

• Studying language model architecture through readable code
• Fine-tuning a model on custom instruction data
• Configuring LoRA training for a single GPU

Create, update, or reuse a repository threat model: a document describing system architecture, attacker capabilities, trust boundaries, and potential security failures. Produce a Markdown model grounded in source evidence for standalone use or a security scan.

• Creating a threat model for a repository
• Updating a model after architecture changes
• Preparing a model for a security scan

Turn a codebase into architecture documentation with Mermaid diagrams. Using the C4 model, a way to describe systems at different levels of detail, the skill explains external relationships, applications, internal components, deployment, and request flows.

• Explaining a system overview to stakeholders
• Documenting relationships between apps and databases
• Mapping internal components of a feature

Implement Mamba, a model architecture that processes sequences through an internal state with computation scaling linearly with input length. Covers pretrained text generation, Mamba-1 and Mamba-2 configuration, speed comparisons with Transformers, and GPU memory troubleshooting.

• Explore models for long sequences or streaming applications
• Generate text with pretrained Mamba models
• Compare Mamba-1 and Mamba-2 configurations

Expert in business model design - the architecture of how a company creates, delivers, and captures value. Covers business model canvas, revenue model selection, value chain design, and business model innovation. Knows when to copy proven models and when to innovate. Use when "business model, revenue model, how to monetize, unit economics, value proposition, business model canvas, business model innovation, " mentioned.

The English summary is being prepared. Showing the original description.

Build and evaluate Mamba models for long sequences using state-space models, which summarize past inputs in an internal state. Covers setup, pretrained text generation, differences between Mamba-1 and Mamba-2, and speed comparisons with Transformers.

• Generate text with pretrained Mamba models
• Compare Mamba-1 and Mamba-2 configurations
• Benchmark generation speed against Transformers

Train Mixture of Experts models, which activate selected specialist networks for each input. The skill guides architecture, input routing, workload balancing, and GPU distribution using DeepSpeed or HuggingFace, with examples for training configuration and inference optimization.

• Designing a model that activates only selected expert networks
• Balancing workloads across expert networks
• Distributing experts across multiple GPUs

Create, update, or reuse a repository threat model: a document describing its architecture, attacker capabilities, trust boundaries, and potential security failures. The result is a Markdown reference grounded in the repository's actual code and scope.

• Documenting architecture and trust boundaries
• Creating or updating a repository threat model
• Preparing a threat model for a specific security review

Learn how GPT language models work by preparing text, training a small model, and generating samples. Covers CPU experiments, custom datasets, further training of pretrained GPT-2 models, and reproducing GPT-2 with multiple GPUs.

• Train a small model on Shakespeare using a CPU
• Prepare custom text for model training
• Further train a pretrained GPT-2 model

Build and train Mixture of Experts models, which activate selected specialist networks for each input. Use DeepSpeed or HuggingFace workflows to configure routing, balance workloads, distribute experts across GPUs, and optimize inference.

• Designing MoE models for a limited compute budget
• Implementing Mixtral-style expert routing
• Adjusting expert workloads and training stability

Learn how GPT language models work by preparing text, training a small model, and generating samples. Covers CPU experiments, custom datasets, further training of pretrained GPT-2 models, and reproducing GPT-2 with multiple GPUs.

• Train a small model on Shakespeare using a CPU
• Prepare custom text for model training
• Further train a pretrained GPT-2 model

Guided journey from an app idea to a deliberate architecture: boundaries, domain model, data decisions, and resilience, making only the expensive-to-reverse decisions and deferring the rest. Orchestrates eight skills phase by phase - clean-architecture, domain-driven-design, system-design, ddia-systems, software-design-philosophy, release-it, pragmatic-programmer, 37signals-way - asking the user questions at every decision point and recording results in the project docs/ folder (ARCHITECTURE.md, DESIGN-CODE-ARCHITECTURE-PLAN.md) so the journey resumes across sessions. Use when the user wants to design a new app's architecture, choose boundaries and a domain model, decide monolith versus microservices, or says 'how should I structure this app'. If a codebase already exists, use remove-technical-debt (aged), improve-code-quality (fresh prototype), or architecture-optimization (slow but working); if unvalidated, run create-business or create-app first. For one framework in isolation, invoke that skill directly.

The English summary is being prepared. Showing the original description.

Bridge Codex to web-based AI model products by packaging local task context, scrub-checking it, sending it through an approved browser surface to ChatGPT Pro, Claude, Grok, Gemini, or another web model, waiting for the answer, and returning the model response to the user or Codex. Also guide DevSpace-like MCP Connector Mode when the user wants ChatGPT Pro or another MCP-capable web host to access approved local workspaces without relying on Codex browser automation. Use when the user asks for GPT Pro, ChatGPT Pro, Claude web, Grok, Gemini web, web model bridge, external model consult, ask another model, second opinion, use a web AI model, browserless agent access to GPT Pro, MCP connector, DevSpace-like workflow, or send local repo context to a browser-based model for planning, review, debugging, architecture discussion, or implementation guidance.

The English summary is being prepared. Showing the original description.

Knowledge base from DoD Architecture Framework (DoDAF) 2.02 — Volume II: Architectural Data and Models. Use for DoDAF viewpoints, DM2 meta-model, capability modeling, operational architecture, systems architecture, services architecture, data/information modeling, standards compliance, project/portfolio integration, and fit-for-purpose model selection. Does not cover DoDAF Volume I (policy/governance) or Volume III (enterprise-level guidance); also does not substitute for the live DISR or DARS registries.

The English summary is being prepared. Showing the original description.

Guide for choosing models in Tinker — available model families, model types (base, instruction, reasoning, hybrid, vision), architecture (dense vs MoE), and how to match renderers to models. Use when the user asks which model to use, what models are available, or how to pick a model for their task.

The English summary is being prepared. Showing the original description.

Review a Power BI data model’s tables, relationships, storage choices, performance, maintainability, and security. Use the findings to identify design issues and build a prioritized improvement plan with concrete recommendations and implementation guidance.

• Reviewing a Power BI model before production release
• Investigating slow queries and oversized models
• Checking table relationships and storage choices

Build a Solution Blueprint for a Dynamics 365 Finance and Supply Chain Management implementation through guided interviews. Define scope and architecture, compare options, and document decisions, their rationale, assumptions, and unresolved questions across working sessions.

• Create an architecture blueprint for a new D365 implementation
• Define implementation scope and rollout phases
• Compare data migration and integration approaches

Analyze a codebase to identify valuable assets, attack entry points, and realistic abuse paths. Produce a concise Markdown threat model that explains risk priorities, distinguishes existing protections from proposed mitigations, and makes assumptions explicit.

• Map attack entry points in a codebase
• Assess threats within a specific project directory
• Prioritize risks to sensitive data and credentials

Analyze a codebase to identify valuable assets, attack entry points, and realistic abuse paths. Produce a concise Markdown threat model that explains risk priorities, distinguishes existing protections from proposed mitigations, and makes assumptions explicit.

• Map attack entry points in a codebase
• Assess threats within a specific project directory
• Prioritize risks to sensitive data and credentials

Create a Markdown threat model grounded in a codebase. Identify valuable assets, boundaries between trusted and untrusted components, realistic attack paths, and mitigations, then prioritize risks using explicit assumptions about likelihood and impact.

• Map attack paths across a codebase
• Assess threats within a specific project directory
• Prioritize risks to data and credentials