vertex-tuning-open-model

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

775|303|Updated May 27, 2021

Search Tags:#mlops #fine-tuning #generative ai #vertex ai #llm tuning #open source models

Ready to run

npx skills add https://github.com/GoogleCloudPlatform/vertex-ai-samples --skill vertex-tuning-open-model

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: vertex-tuning-open-model
Source: https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/skills/vertex-tuning/open-model
Command: npx skills add https://github.com/GoogleCloudPlatform/vertex-ai-samples --skill vertex-tuning-open-model

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 open-source Large Language Models (LLMs) using Google Cloud's Vertex AI platform, making advanced model customization accessible.

Core Features & Use Cases

End-to-End Workflow: Guides users through environment setup, data preparation, model configuration, job submission, monitoring, and deployment.
Data Handling: Supports conversion and validation of datasets into the required JSONL format.
Model & Hyperparameter Tuning: Assists in selecting appropriate open models and configuring essential hyperparameters like learning rate and epochs.
Use Case: A data scientist needs to adapt an open-source LLM for a specific customer support task. They can use this Skill to prepare their conversational data, tune the model on Vertex AI, and then deploy the fine-tuned model for inference.

Quick Start

Use the vertex-tuning-open-model skill to fine-tune the Gemma 3 1B IT model with your dataset located at gs://my-bucket/my-data.jsonl.

Frequently Asked Questions about vertex-tuning-open-model

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

FAQPage Schema

How do I fine-tune an open-source LLM like Llama or Gemma on Vertex AI?▼

Fine-tuning open-source LLMs on Vertex AI involves managing an end-to-end workflow using Python scripts. The process covers data preparation in JSONL format, model selection, hyperparameter tuning, job submission, monitoring, and deployment to Vertex AI endpoints.

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

Datasets for Vertex AI LLM tuning must be converted and validated into the JSONL format. This data handling step ensures the conversational or instructional data aligns with the expected input structure for models like Gemma or Qwen.

Can I use PEFT for fine-tuning open models on Google Cloud Vertex AI?▼

Yes, you can use PEFT for fine-tuning open models on Google Cloud Vertex AI. The workflow supports both full parameter and PEFT tuning, allowing you to efficiently adapt large language models while managing compute resources.

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

To deploy a fine-tuned open LLM to a Vertex AI endpoint, you submit a tuning job via Python scripts, monitor the training process, and then deploy the resulting customized model directly through the Vertex AI platform for inference.

Do I need the google-cloud-aiplatform library to submit a Vertex AI tuning job?▼

Yes, you need the google-cloud-aiplatform library to submit a Vertex AI tuning job. It is a required dependency for managing the environment setup, job submission, and deployment lifecycle on Google Cloud.