About

Blog

Lumino

API Reference

Get Early Access

The price is based on 1M (1,000,000) token data set size, and per one epoch.

Fine-Tuning Pricing

Welcome to Lumino AI, a cutting-edge fine-tuning platform that empowers you to customize open-source large language models to suit your specific needs. Whether you’re an AI researcher, developer, or enthusiast, Lumino AI provides the tools and infrastructure to make fine-tuning efficient, scalable, and user-friendly.

Introduction

Fine-tuning Large Language Models (LLMs) is a specialized process within machine learning that adapts pre-trained language models to perform specific tasks or to better understand particular domains. Given the immense capabilities and versatility of LLMs like Llama3, fine-tuning allows these models to deliver more accurate, relevant, and context-aware outputs tailored to specific applications or industries.

Overview

Once you’ve optimized your prompt and have identified specific areas where the model still needs improvement, it’s time to prepare your data for fine-tuning. The key here is to curate a comprehensive dataset that closely mirrors the interactions or responses your model will handle in production.

On the Lumino Dashboard UI, go to the Datasets tab and click on Upload Dataset.

Upload Training Dataset

On the Lumino Dashboard UI, go to the Fine-tuning tab and click on Create Job.

Fine Tuning Models

Tutorial: Fine Tune Llama3.1 8B with Lumino SDK

FAQs

Error Codes

List all API keys for the current user

Create a new API key

Get details of a specific API key

Revoke a specific API key

Update a specific API key

Get current user information

Update current user information

List all available base LLM models

Get detailed information about a specific base model

List all fine-tuned models for the current user

Get detailed information about a specific fine-tuned model

Get total cost for a given period

Get a list of usage records for a given period

List all fine-tuning jobs

Create a new fine-tuning job

Get details of a specific fine-tuning job

Cancel a fine-tuning job

List all datasets uploaded by the user

Upload a new dataset file

Get information about a specific dataset

Delete a specific dataset file

Update a specific dataset's information

Redirect to Stripe for adding credits

Get credit history for the current user

Model	Type of Finetuning	Price
Llama 3.1 8B	qLoRA	$2
Llama 3.1 8B	LoRA	$2
Llama 3.1 8B	Full Finetuning	$2
Llama 3.1 70B	LoRA	$10
Llama 3.1 70B	Full Finetuning	$10

Getting Started

Fine-Tuning

Pricing

Frequently Asked Questions

Fine-Tuning Pricing