“models”的搜索结果

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。

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

Call Gemini and OpenMaaS models such as Llama, DeepSeek, and Qwen through Google Cloud Agent Platform. Prepare authentication and SDK code, run prompts, configure connection endpoints, and troubleshoot common request errors.

中文简介正在准备中。当前显示英语简介。

• Send a test prompt to Gemini
• Call Llama or DeepSeek with the OpenAI SDK
• Write code to call an existing custom endpoint

Manage machine learning models and their versions in the Agent Platform Model Registry. List registered models, inspect details, upload new versions, update names or descriptions, and delete models through workflows that require confirmation for changes.

中文简介正在准备中。当前显示英语简介。

• List registered models and inspect their details
• Register a new model or model version
• Update a model's display name or description

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。

• Extracting company or profile details into JSON
• Classifying text using a fixed set of labels
• Generating text that matches a specified pattern

Fine-tune vision models on custom images using Hugging Face Jobs cloud GPUs. Covers object detection, image classification, and segmentation—identifying image regions—with dataset validation, hardware selection, cost estimates, monitoring, and saving trained models to the Hub.

中文简介正在准备中。当前显示英语简介。

• Train an object detector on custom images
• Fine-tune an image classifier
• Adapt SAM/SAM2 to custom image masks

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。

• Interpret regression coefficients and confidence intervals
• Model binary outcomes or event counts
• Forecast time series with uncertainty intervals

Build and estimate economic models that represent underlying choices and incentives. Get guidance on demand, dynamic choice, and auction models, select estimation methods, and diagnose numerical problems such as failed convergence or sensitivity to starting values.

中文简介正在准备中。当前显示英语简介。

• Choose an estimation method for a structural economic model
• Implement BLP demand estimation
• Estimate dynamic choice and auction models

Develop Bayesian models for quantitative social science, from choosing priors to reporting posterior results. Guide MCMC, a sampling method for estimating distributions, check convergence, and assess sensitivity for hierarchical models and small datasets.

中文简介正在准备中。当前显示英语简介。

• Choosing priors for models with small datasets
• Implementing hierarchical models in Stan or PyMC
• Investigating MCMC convergence problems

Deploy AI models to embedded hardware using MathWorks tools (MATLAB, Simulink, Embedded Coder). Covers two workflow patterns: (1) MathWorks-native or imported models rebuilt as dlnetwork for lean hardware, (2) direct C/C++ code generation from PyTorch and LiteRT models. Both patterns support all targets (Cortex-M/A/R, x86, GPU). Trigger when: user wants to deploy AI to embedded targets; generate C/CUDA from neural networks; compress AI models for MCU; integrate AI in Simulink for system-level simulation; import PyTorch/ONNX/TensorFlow models for embedded deployment; optimize AI for resource-constrained hardware; or use loadPyTorchExportedProgram, loadLiteRTModel, importNetworkFromPyTorch, importNetworkFromONNX, importNetworkFromTensorFlow, importNetworkFromKeras, dlquantizer, exportNetworkToSimulink, or Embedded Coder with AI models.

中文简介正在准备中。当前显示原文说明。

Deploy AI models to embedded hardware using MathWorks tools (MATLAB, Simulink, Embedded Coder). Covers two workflow patterns: (1) MathWorks-native or 3P-imported models rebuilt as dlnetwork for lean hardware (Cortex-M, DSP), (2) direct C/C++ code generation from PyTorch and LiteRT models for high-performance hardware (Cortex-A, x86, GPU). Trigger when: user wants to deploy AI to embedded targets; generate C/CUDA from neural networks; compress AI models for MCU/DSP; integrate AI in Simulink for system-level simulation; import PyTorch/ONNX/TensorFlow models for embedded deployment; optimize AI for resource-constrained hardware; or use loadPyTorchExportedProgram, importNetworkFromPyTorch, dlquantizer, exportNetworkToSimulink, or Embedded Coder with AI models.

中文简介正在准备中。当前显示原文说明。

Sync OpenRouter models used by OpenClaw into this installation's config. Fetches the OpenClaw app leaderboard from OpenRouter, verifies model IDs against the API catalog, and adds missing models with correct specs and aliases. Use when asked to "sync openrouter models", "add missing models", "update openrouter config", or "check openrouter models".

中文简介正在准备中。当前显示原文说明。

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。

• Load larger models within limited GPU memory
• Compare 8-bit and 4-bit model settings
• Fine-tune a model with QLoRA

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。

• Compare models on standard knowledge and reasoning tests
• Track model performance across training checkpoints
• Organize evaluation results for research reports

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。

• Combining math, coding, and conversation capabilities
• Blending two models at different ratios
• Comparing variants made with different merging methods

Convert Snowflake dbt SQL models to BigQuery through a bulk migration workflow. Preserve Jinja template logic while adapting configuration, explicit type conversions, JSON access, and deduplication patterns, with translated files saved in their directory structure.

中文简介正在准备中。当前显示英语简介。

• Migrating Snowflake dbt models to BigQuery in bulk
• Preserving dbt references and incremental processing logic
• Adapting JSON, array, and STRUCT access during migration

Combine specialized language models without retraining using mergekit. The skill explains how to choose merging methods, configure each model’s contribution, compare resulting variants, and prepare a merged model for evaluation and deployment.

中文简介正在准备中。当前显示英语简介。

• Combine math, coding, and conversation capabilities
• Compare model variants with different merge weights
• Choose a method for merging several models

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.

中文简介正在准备中。当前显示英语简介。

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

Compress large language models to 4-bit weights to reduce GPU memory needs and accelerate text generation. Covers loading compressed models, converting your own models, choosing settings, and preparing memory-efficient fine-tuning with transformers and PEFT.

中文简介正在准备中。当前显示英语简介。

• Run language models with limited GPU memory
• Convert your own model to 4-bit weights
• Compare compression settings for quality and speed

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。

• Compare models on standard knowledge and reasoning tests
• Track model performance across training checkpoints
• Organize evaluation results for research reports

Adapt large language models to specific tasks through fine-tuning, or additional training. Prepares and validates datasets, configures LoRA or QLoRA to train a small subset of parameters, and supplies training settings, evaluation scripts, and deployment optimization guidance.

中文简介正在准备中。当前显示英语简介。

• Preparing and validating JSONL training data
• Choosing LoRA or QLoRA for available GPU memory
• Configuring training and monitoring overfitting

Maintain Kiln’s list of large language models by discovering new releases, testing provider access, and marking unavailable entries as deprecated. Prepare pull requests, report unresolved issues, and check whether the updated list needs publication.

中文简介正在准备中。当前显示英语简介。

• Run the scheduled model sweep manually
• Add new models and test provider access
• Mark unavailable model entries as deprecated

Turn regression results and summary statistics from Stata, R, or Python into LaTeX tables for academic papers. Format model comparisons, decimal places, statistical significance markers, and notes, with guidance for wide tables and inclusion in a paper.

中文简介正在准备中。当前显示英语简介。

• Comparing several regression models in one table
• Formatting summary statistics for a paper
• Combining results into a table with multiple panels

Run inference on Fireworks AI — direct, through the Leanmcp AI Gateway proxy (aigateway.leanmcp.com) for observability, or via LiteLLM / the OpenAI SDK / raw HTTP. Covers the endpoint-and-key matrix for each route, serverless vs dedicated deployments and their cold starts, browsing and filtering the model catalogue, reasoning models that return content:null with the answer in reasoning_content, function calling, concurrency and load testing, and runner scripts where many models share one protocol with a --use-proxy toggle. Use this skill whenever the user mentions Fireworks, FIREWORKS_API_KEY, api.fireworks.ai, fireworks_ai/ model ids, accounts/fireworks/models/..., a Fireworks deployment id, the Leanmcp gateway or LEANMCP_API_KEY, app.leanmcp.com observability, or gpt-oss / kimi / glm / qwen / deepseek served on Fireworks; wants to route LLM calls through a proxy for logging or cost tracking; is debugging empty responses, 404s, scope errors, cold starts, or "the gateway isn't working"; wants to pick a Fireworks model with tool calling; or wants to sweep several models over one benchmark. Reach for it even on vague asks like "why is this model returning nothing" or "set up inference for these models" when Fireworks is in play.

中文简介正在准备中。当前显示原文说明。

Define database models with clear naming, appropriate data types, constraints, relationships, and validation at multiple layers. Use this skill when creating or modifying database model files, ORM classes, schema definitions, or data model relationships. Apply when working with model files (e.g., models.py, models/, ActiveRecord classes, Prisma schema, Sequelize models), defining table structures, setting up foreign keys and relationships, configuring cascade behaviors, implementing model validations, adding timestamps, or working with database constraints (NOT NULL, UNIQUE, foreign keys). Use for any task involving data integrity enforcement, relationship definitions, or model-level data validation.

中文简介正在准备中。当前显示原文说明。