Results for “model-preset”

Manage machine learning models in the Agent Platform Model Registry: list, describe, upload, update, and delete models and their versions.

Fine-tune open models or Gemini models using Agent Platform infrastructure, from environment setup through data preparation, job configuration, monitoring, and deployment.

Create Earth2Studio prognostic model wrappers that time-step weather forecasts forward, with triple-inheritance classes, tests, and documentation.

Cross-model benchmark for gstack skills. (gstack)

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining, covering SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

Turn model work into a production ML system with data contracts, reproducible training, quality gates, deployable artifacts, and monitoring.

Every metric encodes an opinion about which mistake hurts.

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

Production machine-learning engineering workflow for data contracts, reproducible training, model evaluation, deployment, monitoring, and rollback. Use when building, reviewing, or hardening ML systems beyond one-off notebooks.

Visual Prompt Tuning

A model in production is never just weights.

Use the model-recommender skill, Workflow D (Setup Questionnaire), to configure model access and project-level preferences.

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

Compress large language models by 40-60% with minimal accuracy loss using one-shot pruning techniques like Wanda and SparseGPT, enabling faster inference and deployment on constrained hardware.

Configure, troubleshoot, and use Hermes image generation — all 5 built-in providers (FAL, OpenAI, OpenAI-Codex, xAI, Krea), model catalogs, env vars, and .env location gotchas.

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.

Train machine learning models end-to-end, covering data loading, preprocessing, architecture selection, training loops, validation, and checkpointing. Use when the user requests model training or provides relevant inputs for this workflow.

Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates with evals.

Train, evaluate, export, and run inference for Masked Auto-Encoder (MAE) models for self-supervised pretraining and fine-tuning of visual representations.

Switch model profile for GSD agents (quality/balanced/budget)

Agent skill for data-ml-model - invoke with $agent-data-ml-model

Recommend model families and validation strategy based on data, constraints, and objective. Use when: (1) choosing algorithms, (2) balancing bias/variance, (3) planning benchmark baselines. NOT for: final legal/compliance sign-off.

Turns model work into a production ML system with data contracts, reproducible training, quality gates, deployable artifacts, and monitoring.

Selects the right Gemma model for a task, recommends deployment tooling (Gradio, Transformers.js, Vertex AI, MLX), and applies optimizations like MTP and QAT.

Inspect and adjust the agent's runtime state, including model, context window, iteration limits, token usage, workspace configuration, subagent status, and request routing metadata.

Remove refusal behaviors from open-weight LLMs using OBLITERATUS — mechanistic interpretability techniques (diff-in-means, SVD, whitened SVD, LEACE, SAE decomposition, etc.) to excise guardrails while preserving reasoning. 9 CLI methods, 28 analysis modules, 116 model presets across 5 compute tiers, tournament evaluation, and telemetry-driven recommendations. Use when a user wants to uncensor, abliterate, or remove refusal from an LLM.