“code models”的搜索结果

Choose embedding models, which represent text as numerical vectors, for meaning-based search and RAG applications. Compare options for code, prose, and multilingual content, and plan document splitting, preprocessing, caching, and dimension reduction to improve retrieval quality.

中文简介正在准备中。当前显示英语简介。

• Choosing an embedding model for RAG
• Reviewing document chunk size and boundaries
• Planning code or specialist document search

Apply psychology and behavioral science to marketing decisions. The skill selects relevant thinking models, explains customer behavior, and suggests ethical changes to pricing, messaging, purchase journeys, and campaign priorities.

中文简介正在准备中。当前显示英语简介。

• Understand why customers hesitate to buy
• Review pricing plans and how prices are presented
• Simplify signup and purchase journeys

Build text tokenizers that split multilingual text into small units for AI models. Learn how to train SentencePiece on raw text, configure BPE or Unigram splitting methods, and convert text to token IDs and back.

中文简介正在准备中。当前显示英语简介。

• Preparing Japanese, Chinese, or Korean text for AI models
• Training a custom vocabulary from raw text
• Choosing between BPE and Unigram

Compress LLM weights using HQQ quantization, which stores weights with fewer bits without calibration datasets. Follow workflows for precision settings, model saving, inference integration, and LoRA fine-tuning of quantized models.

中文简介正在准备中。当前显示英语简介。

• Compressing LLMs without calibration datasets
• Serving quantized models with vLLM or HuggingFace Transformers
• Comparing bit widths and inference backends

Reduce the memory needed to run large language models with GPTQ quantization, which stores model weights at lower precision. Covers loading compressed models, quantizing your own models, choosing execution backends, and connecting to memory-efficient fine-tuning.

中文简介正在准备中。当前显示英语简介。

• Run a language model within limited GPU memory
• Load a pre-quantized model for text generation
• Quantize and save your own trained model

Guide reinforcement learning, training models through rewards, with slime. Prepare data, configure Megatron-LM training and SGLang response generation, and set up asynchronous runs or custom multi-turn workflows for supported language models.

中文简介正在准备中。当前显示英语简介。

• Preparing reward-based training for GLM or Qwen models
• Overlapping response generation and training
• Training agents that use tools across multiple turns

Get guidance on adapting large language models with Axolotl. Covers YAML configuration files, LoRA and QLoRA methods for training fewer parameters, distributed training settings, dataset formats, and debugging training code.

中文简介正在准备中。当前显示英语简介。

• Write YAML settings for model fine-tuning
• Explore training with LoRA or QLoRA
• Configure training across multiple GPUs

Adapt machine learning training to run across multiple GPUs or machines with Ray Train. Covers changes to existing code, comparing training settings with Ray Tune, and saving checkpoints so training can resume after failures.

中文简介正在准备中。当前显示英语简介。

• Adapting existing PyTorch code for multiple GPUs
• Training HuggingFace models across multiple machines
• Comparing learning rates and batch sizes with Ray Tune

Helps configure and troubleshoot DeepSpeed for training large models across multiple devices. Covers memory optimization, parallel training, and DeepNVMe storage transfers, with examples for tuning data movement and configuring models that divide work among specialized components.

中文简介正在准备中。当前显示英语简介。

• Configuring distributed training for large models
• Tuning tensor transfers to NVMe storage
• Setting up models with specialized expert components

Helps speed up LLM text generation by comparing methods that predict and verify multiple tokens at once. Covers draft model selection, Medusa prediction heads, Lookahead Decoding settings, and deployment examples for inference services.

中文简介正在准备中。当前显示英语简介。

• Reducing chatbot response latency
• Comparing methods for faster code generation
• Selecting a small draft model for a larger LLM

Reduce LLM generation delays with speculative decoding, which proposes tokens ahead of verification. This skill compares small draft models, Medusa, and Lookahead Decoding, with implementation examples, tuning guidance, and deployment using vLLM.

中文简介正在准备中。当前显示英语简介。

• Reducing response delays in chatbots
• Speeding up code generation
• Choosing a small model to draft candidate tokens

Get guidance on adapting LLMs through additional training with LLaMA-Factory. The skill covers a visual interface requiring no code, LoRA and QLoRA training methods, and documentation-based help with implementation, features, and debugging.

中文简介正在准备中。当前显示英语简介。

• Learning additional training through a visual interface
• Exploring LoRA and QLoRA training methods
• Checking supported models and multimodal features

Build text tokenizers, which split text into units for AI models, directly from raw multilingual text. Learn custom vocabularies with BPE or Unigram, convert text to pieces or numeric IDs, and decode the results.

中文简介正在准备中。当前显示英语简介。

• Preparing text for multilingual AI models
• Training a vocabulary from Japanese text
• Reusing a tokenizer for reproducible text splitting

Choose a serving container for models deployed on SageMaker. Match the model type to a compatible image, retrieve its address from the AWS catalog, and check regional availability, CPU or GPU variants, and required host settings.

中文简介正在准备中。当前显示英语简介。

• Choose a container for an LLM deployment
• Select images for embeddings and rerankers
• Check regional image addresses and GPU compatibility

Manage agents on a host by listing their capabilities, reading source code, and downloading or deploying agents in the smith namespace. Check available language model connections and their roles without exposing API keys.

中文简介正在准备中。当前显示英语简介。

• Find available agents and check their capabilities
• Study existing agent source code
• Download and deploy smith agents for editing

Turn cryptographic code or specifications into sequence diagrams showing who sends each message, which cryptographic operations occur, and where failures stop the exchange. Outputs include Mermaid source, a plain text diagram, and a protocol summary.

中文简介正在准备中。当前显示英语简介。

• Visualizing handshake and key exchange steps
• Extracting message flows from RFCs and papers
• Diagramming ProVerif or Tamarin models

Search GitHub, Stack Overflow, Hacker News, and HuggingFace for code examples, projects, technical answers, discussions, models, datasets, and Spaces. Filter supported searches and receive structured JSON results containing titles, links, and snippets.

中文简介正在准备中。当前显示英语简介。

• Find code examples and open-source projects
• Search technical answers and GitHub Issues
• Explore developer news and discussions

Write and review R analysis scripts for a sewage research project using its established conventions. Estimate requested regression models, add specifications, and save LaTeX tables, figures, and model objects for use in the research paper.

中文简介正在准备中。当前显示英语简介。

• Estimate models of sewage spills and property prices
• Add specifications to an existing regression analysis
• Create descriptive plots and maps

Analyze datasets in R or Python, from exploring distributions and missing values to fitting regressions. Produce tables and figures for publication, save scripts and model results, and review the analysis for common problems.

中文简介正在准备中。当前显示英语简介。

• Explore distributions, missing values, and relationships
• Run regressions on cross-sectional or panel data
• Export publication-ready regression tables and figures

Build and evaluate Bayesian models with PyMC and ArviZ, from choosing initial assumptions to checking predictions. The workflow covers sampling diagnostics, model comparison, and reports that explain results with uncertainty intervals.

中文简介正在准备中。当前显示英语简介。

• Choose and check prior distributions
• Investigate sampling and convergence problems
• Compare hierarchical or regression models

Survey a whole React codebase as a senior React engineer, using React Doctor's scan as evidence, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the React code", "audit this codebase", "make this app faster / more robust", or wants a roadmap of fixes rather than a review of a single diff. For a regression check or a fix-it-now pass, use the `react-doctor` skill instead.

中文简介正在准备中。当前显示原文说明。

Use when the user wants to migrate code that calls OpenAI, Gemini/Google AI, or the Anthropic API to Amazon Bedrock — a pure model/SDK rewrite. End-to-end: assesses the codebase, rewrites SDK calls, evaluates output quality against Bedrock, and delivers a ready-to-merge git branch. Also has an access-only mode for checking or enabling Bedrock model access for specific models (e.g. 'request access to Claude on Bedrock', 'which models do I turn on') with no code migration — it checks each model and walks the right access step, then stops. Not for agent runtime selection or agent migration planning (use agent-advisor), nor standalone cost estimates or infra-only migration. The full migration REQUIRES gcp-to-aws OR azure-to-aws installed alongside this skill (gcp-to-aws preferred when both are present); access-only mode needs neither.

中文简介正在准备中。当前显示原文说明。

Sets up and maintains isolated Claude Code CLI profiles to run Kimi, MiniMax, DeepSeek, GLM, StepFun or Anthropic in separate terminal windows. Use for multi-provider setup, switching models, csk/csd/csg aliases, CLAUDE_CONFIG_DIR, or ~/.claude-profiles. Owns profile-drift troubleshooting (missing skills/hooks, symlink drift, settings drift) and context-window setup ([1m] marker vs CLAUDE_CODE_MAX_CONTEXT_TOKENS).

中文简介正在准备中。当前显示原文说明。

Reapply and repair Windows Codex Desktop after Store upgrades, including custom provider models hidden by Statsig available_models filtering, the dependent blue-purple Power slider and its Ultra toggle, Fast Mode request/UI gates, locale i18n, plugin UI gates, Chrome/browser_use gates, Goal command gates, Windows Computer Use availability gates and plugin/runtime repair, phone remote-control pairing under third-party/API-key main app usage, Desktop dynamicTools/inputSchema thread-start schema drift, local conversation visibility recovery after model_provider switches, restored-conversation missing-cwd continuation repair, ASAR integrity repair, signing/installing patched MSIX packages, SDK cleanup, Fast Mode wire verification, local plugin marketplace registration, and optional custom model_instructions_file setup (the bundled system prompt, also called 听话水).

中文简介正在准备中。当前显示原文说明。