praisonai.train

Wrapper This script finetunes a model using Unsloth’s fast training framework. It supports both ShareGPT and Alpaca‑style datasets by converting raw conversation data into plain-text prompts using a chat template, then pre‑tokenizing the prompts. Extra debug logging is added to help trace the root cause of errors.

Overview

This module provides components for train.

Classes

TrainModel

Class definition.

Functions

formatting_prompts_func()

Converts each example’s conversation into a single plain-text prompt.

tokenize_function()

Tokenizes a batch of text prompts with padding and truncation enabled.

main()

Function definition.

train_visionThis script finetunes a vision language model using Unsloth's fast training framework.

⌘I

praisonai.train
Overview
Classes
Functions