592 个 · 按相关度排序
Compress large language models to 4-bit weights to reduce GPU memory use and accelerate inference. Covers loading compressed models, configuring quantization, and using Transformers or vLLM, with guidance on hardware requirements and backend choices.
中文简介正在准备中。当前显示英语简介。
Train smaller language models using knowledge distillation, where a larger model supplies examples or prediction targets. This skill covers training losses, generated training data, parameter choices, and output comparisons to support model compression and specialized student models.
中文简介正在准备中。当前显示英语简介。
Combine capabilities from multiple fine-tuned LLMs without retraining using mergekit. Choose a merging method, configure how models are blended, and evaluate the resulting model on tasks such as math, code generation, and conversation.
中文简介正在准备中。当前显示英语简介。
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.
中文简介正在准备中。当前显示英语简介。
Explore local or remote repositories with Repomix CLI to understand their structure, locate related code across files, and review file counts and estimated tokens, the units AI models use to process text.
中文简介正在准备中。当前显示英语简介。
Test Qwen Code CLI behavior from model requests through tool execution. Reproduce bugs, check terminal interactions and MCP tool connections, and inspect API logs using real models or mock servers for controlled scenarios.
中文简介正在准备中。当前显示英语简介。
Review board memos and strategy briefs with available Claude, Codex, and Gemini models. Compare concerns, supporting arguments, and votes, then turn disagreements into questions to resolve before committing to a major business decision.
中文简介正在准备中。当前显示英语简介。
Prepare files for printing on Bambu Lab printers by opening sliced files in Bambu Connect or unsliced models in Bambu Studio. The user selects the printer, checks the setup, and starts printing in the app.
中文简介正在准备中。当前显示英语简介。
Use Outlines to make language models produce data in a defined format. The skill covers extracting information into JSON, restricting classification labels, and applying Pydantic models, which define fields and data types, with local model backends.
中文简介正在准备中。当前显示英语简介。
Select relevant code using Trailmark's map of function relationships, then delegate explanation, review, or edit proposals to a smaller model. Limit the supplied source, check cited evidence, and verify proposed changes before applying them.
中文简介正在准备中。当前显示英语简介。
Review domain code for classes that hold data while business logic lives elsewhere. Using domain-driven design patterns, diagnose problems and refactor objects to keep business rules, state changes, and validation together, with before-and-after diffs.
中文简介正在准备中。当前显示英语简介。
Fit regression and time series models in Python, then examine coefficients, uncertainty, and predictions. Check model assumptions, investigate unusual observations, and compare alternatives using detailed statistical summaries and diagnostic tests.
中文简介正在准备中。当前显示英语简介。
Use the skill to control and verify the code interface configuration of your model — how Simulink® model elements are represented in the generated C or C++ code. This includes — (1) specifying names, types (storage classes), and placement of variables that represent model elements (for example, making a model parameter tunable as a global extern variable); (2) specifying names, types, and placement of functions that represent model algorithms; (3) selecting the deployment type (Component, Subcomponent, or Automatic); (4) selecting the interface configuration type (data or service interface); (5) linking a shared Embedded Coder dictionary to a model; (6) creating Embedded Coder dictionary entries and setting their properties; (7) for service interface configuration — specifying service interface definitions, including sender, receiver, client, and server services. Items 1 and 2 can be set per element or as a category-wide default. Item 1 applies to GRT and ERT models; the rest to ERT models only.
中文简介正在准备中。当前显示原文说明。
Build with DeepSeek Coder — open code models with strong reasoning and long-context code understanding.
中文简介正在准备中。当前显示原文说明。
Build with Meta's Code Llama — open code models for generation, infilling, and long-context code tasks.
中文简介正在准备中。当前显示原文说明。
Build with Mistral's Codestral code models — efficient open code generation with fill-in-the-middle.
中文简介正在准备中。当前显示原文说明。
Orientation for custom (non-OpenAI) models running in the Codex app through the codex-router proxy. Explains that the app's native tools arrive as flattened codex_app__ and mcp__ names, that the router restores them so the app executes them, which companion skills to read before threads, browser, or computer-use work, and that a turn with no tool call ends the task. Use when the session uses a custom (non-OpenAI) model, for example deepseek-v4-flash or mimo-v2.5, when codex_app__ or mcp__ tool names appear in the tool list, when a tool result just arrived and more work remains, or when thread, browser, or computer-use work is requested.
中文简介正在准备中。当前显示原文说明。
[BETA] Detect, review, and fix code-quality and correctness issues in an AEM as a Cloud Service project — locally, with no external services or network calls. Use whenever a user wants to check, review, assess, audit, scan, modernize, upgrade, or fix AEM Java, Sling Models, OSGi, or Maven code — for example: "check my Sling Models are implemented correctly", "review my @Inject usage", "are my Maven dependencies up to date", "scan this AEM project for issues", "modernize my Sling Models", or "fix code-quality problems". Name the files to assess, or ask it to scan the repo; it detects issues, plans, and — only when you ask — applies surgical edits on a branch or in place, then verifies with mvn compile. It recognises the intent and handles each issue type itself, reporting anything it cannot yet fix. This skill is in beta. Verify all outputs before applying them to production projects.
中文简介正在准备中。当前显示原文说明。
使用统一任务评估大语言模型的知识、推理和代码生成能力，生成多模型对比表及训练阶段的成绩趋势，并保存评估结果和每道题的回答。
Assess language models with over 60 academic benchmark tests using consistent prompts and scoring. Compare models, track performance during training, and organize research results with support for HuggingFace models, vLLM, and APIs.
中文简介正在准备中。当前显示英语简介。
Helps adapt LLMs to specific tasks with LLaMA-Factory, including training through a web interface and memory-saving methods such as QLoRA. Provides documentation references for learning features, implementing workflows, and investigating code problems.
中文简介正在准备中。当前显示英语简介。
Reduce GPU memory use by loading language models in 8-bit or 4-bit formats with bitsandbytes and HuggingFace Transformers. Includes configuration examples, QLoRA fine-tuning of compressed models, and optimizers that reduce memory needed during training.
中文简介正在准备中。当前显示英语简介。
Generate images from written descriptions through 9Router using a choice of image models. Check each model’s supported settings, request an image, and receive a URL, encoded image data, or image bytes for saving to a file.
中文简介正在准备中。当前显示英语简介。
Switch a NanoClaw agent group to a local Ollama model by configuring environment variables and model settings. The skill covers setup checks, optional blocking of Anthropic API access, verification, troubleshooting, and switching back to Claude.
中文简介正在准备中。当前显示英语简介。