Skip to main content

​
Help System

The AITraining CLI has a comprehensive help system.

​
General Help

See all available commands: 
aitraining --help
Output shows:
  • Available subcommands
  • Global options
  • Usage examples

​
Command Help

Get help for a specific command: 
aitraining llm --help
aitraining text-classification --help
aitraining chat --help

​
Trainer-Specific Help

For LLM training, parameters vary by trainer. View trainer-specific help: 
# SFT trainer parameters
aitraining llm --trainer sft --help

# DPO trainer parameters
aitraining llm --trainer dpo --help

# ORPO trainer parameters
aitraining llm --trainer orpo --help

# PPO trainer parameters
aitraining llm --trainer ppo --help

​
Preview Mode

Preview help for a trainer without setting it: 
aitraining llm --preview-trainer dpo --help
This shows DPO parameters without committing to DPO training.

​
Parameter Groups

Help output organizes parameters into groups:
  • Basic - Model, data, project settings
  • Data Processing - Text columns, chat templates, tokenization
  • Training Configuration - Trainer, logging, saving
  • Training Hyperparameters - LR, epochs, batch size
  • PEFT/LoRA - Adapter settings
  • DPO/ORPO - Preference learning params
  • Hub Integration - Push to Hugging Face
  • Knowledge Distillation - Teacher-student params
  • Hyperparameter Sweep - Auto-tuning options
  • Enhanced Evaluation - Advanced metrics
  • Advanced Features - Custom loss, custom metrics
  • Reinforcement Learning - PPO settings
  • Inference - Inference prompts and generation params

​
Finding Parameters

​
By Name

Search help output: 
aitraining llm --help | grep lora

​
By Group

Look for section headers in help output: 
PEFT/LoRA:
  --peft                Enable LoRA training
  --lora-r              LoRA rank (default: 16)
  --lora-alpha          LoRA alpha (default: 32)

​
Quick Reference

CommandPurpose
aitraining --helpAll commands
aitraining llm --helpLLM training options
aitraining llm --trainer X --helpTrainer-specific options
aitraining chat --helpChat interface options

​
Next Steps

LLM Training

Train language models

YAML Configs

Configuration files