skills.rest
GoogleCloudPlatform
GoogleCloudPlatformOFFICIAL
Explore all skills by this author →
WebsiteGitHub

vertex-tuning

Fine-tune large language models on Google Cloud Vertex AI with JSONL data preparation.

775|303|Updated May 27, 2021
Search Tags:#machine learning#gemini#generative ai#vertex ai#model fine-tuning#llm tuning#open models
One-click install
npx skills add https://github.com/GoogleCloudPlatform/vertex-ai-samples --skill vertex-tuning
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vertex-tuning
Source: https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/skills/vertex-tuning
Command: npx skills add https://github.com/GoogleCloudPlatform/vertex-ai-samples --skill vertex-tuning

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-cloud-aiplatform, datasets, smart_open, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill streamlines the process of fine-tuning Large Language Models (LLMs) using Vertex AI's managed services, simplifying complex ML workflows.

Core Features & Use Cases

  • Data Preparation: Converts and validates datasets for Vertex AI tuning.
  • Model Tuning: Submits and monitors tuning jobs for various open and Gemini models.
  • Model Deployment: Deploys tuned models to Vertex AI Endpoints.
  • Use Case: Fine-tune a Llama 3.1 8B model for a specific text classification task using your custom dataset on Vertex AI.

Quick Start

Use the vertex-tuning skill to fine-tune a Llama 3.1 8B model for text classification on Vertex AI.

Frequently Asked Questions about vertex-tuning

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I fine-tune a Llama 3.1 8B model on Vertex AI for text classification?▼

To fine-tune a Llama 3.1 8B model on Vertex AI, this skill handles the end-to-end lifecycle: preparing your custom dataset into JSONL format, submitting the tuning job, monitoring progress, and deploying the customized model to an endpoint.

Can I use the vertex-tuning skill to fine-tune Google's Gemini models?▼

Yes, the vertex-tuning skill supports fine-tuning both open-source models and Google's Gemini family. It configures the necessary tuning parameters and manages the customization workflow directly on the Vertex AI platform.

What data format is required for Vertex AI model tuning?▼

Vertex AI model tuning requires data to be formatted correctly in JSONL. The skill facilitates this by converting and validating your datasets to ensure they meet Vertex AI's managed service requirements before submission.

How do I deploy a fine-tuned LLM to a Vertex AI Endpoint?▼

After your tuning job completes, the skill manages model deployment to Vertex AI Endpoints. This step is built into the end-to-end lifecycle, taking your customized model from training completion to a live inference endpoint.

Do I need the google-cloud-aiplatform library to run LLM tuning jobs?▼

Yes, the google-cloud-aiplatform library is a required dependency. The skill relies on this Python package to interact with Vertex AI services for submitting tuning jobs, monitoring status, and handling deployment.

What is the best way to manage the end-to-end lifecycle of custom LLMs on Vertex AI?▼

The best way to manage the end-to-end lifecycle of custom LLMs on Vertex AI is using an automated skill that handles data preparation, job submission, monitoring, and deployment. This streamlines complex ML workflows for both open and Gemini models.

Related Skills

Explore More Software Engineering Skills→
GoogleCloudPlatformGoogleCloudPlatform
775

vertex-tuning-gemini

Fine-tune Gemini models on Vertex AI with JSONL data and Python scripts.

Official
Advanced
GoogleCloudPlatformGoogleCloudPlatform
775

vertex-tuning-open-model

Fine-tune open-source LLMs on Google Cloud Vertex AI with JSONL data.

Official
Advanced
EdwinFerminEdwinFermin

firebase-vertex-ai

Integrate Firebase projects with Vertex AI for embeddings and analysis pipelines.

Community
Advanced
faionfaionfaionfaion
4

faion-ml-engineer

Guide LLM integration, RAG pipelines, agent development, and model evaluation.

Community
Advanced