Method CreateTrainingObject

Namespace

LMKit.TextAnalysis

Assembly

LM-Kit.NET.dll

CreateTrainingObject(IList<string>, IList<(string, string)>, int)

Creates an object for fine-tuning a categorization model using provided training data.

public LoraFinetuning CreateTrainingObject(IList<string> categories, IList<(string, string)> trainingData, int maxSamples = 1000)

Parameters

categories IList<string>

A list of predefined categories. Each category should be a unique, non-null string.

trainingData IList<(string, string)>

A list of tuples where each tuple contains a text and its corresponding category.

maxSamples int

The maximum number of training samples to use. The default value is 1000.

Returns

LoraFinetuning

A LoraFinetuning object for fine-tuning the categorization model.

Examples

using LMKit.Model;
using LMKit.TextAnalysis;
using LMKit.Finetuning;
using System;
using System.Collections.Generic;

class Example
{
    static void Main()
    {
        Uri modelUri = new Uri("https://your-model-link-here");
        LM model = new LM(modelUri);

        Categorization categorization = new Categorization(model);

        var categories = new List<string> { "food", "technology", "travel" };
        var trainingData = new List<(string, string)>
        {
            ("Pizza is delicious.", "food"),
            ("Quantum computing can change the world.", "technology"),
            ("Visiting Tokyo next year!", "travel")
        };

        try
        {
            LoraFinetuning fineTuner = categorization.CreateTrainingObject(categories, trainingData);
            Console.WriteLine("Training object created successfully. Ready for fine-tuning steps.");
        }
        catch (Exception ex)
        {
            Console.WriteLine($"Error: {ex.Message}");
        }
    }
}

Exceptions

ArgumentNullException

Thrown if the categories or trainingData arguments are null.

ArgumentException

Thrown if the trainingData list is empty, or if an entry is associated with an undefined category.

InvalidModelException

Thrown if fine-tuning is not supported for Embedding classification mode.