aitraining llm --train \
  --model google/gemma-2-2b \
  --data-path ./preferences.jsonl \
  --project-name gemma-orpo \
  --trainer orpo \
  --prompt-text-column prompt \
  --text-column chosen \
  --rejected-text-column rejected \
  --peft

from autotrain.trainers.clm.params import LLMTrainingParams
from autotrain.project import AutoTrainProject

params = LLMTrainingParams(
    model="google/gemma-2-2b",
    data_path="./preferences.jsonl",
    project_name="gemma-orpo",

    trainer="orpo",
    prompt_text_column="prompt",
    text_column="chosen",
    rejected_text_column="rejected",
    dpo_beta=0.1,  # Default: 0.1
    max_completion_length=None,  # Default: None

    epochs=3,
    batch_size=2,
    lr=5e-5,

    peft=True,
    lora_r=16,
)

project = AutoTrainProject(params=params, backend="local", process=True)
project.create()

{
  "prompt": "What is AI?",
  "chosen": "AI is artificial intelligence, a field of computer science focused on creating systems that can perform tasks requiring human intelligence.",
  "rejected": "AI is just robots."
}

params = LLMTrainingParams(
    model="Qwen/Qwen3.5-VL-9B",
    trainer="orpo",
    image_column="images",
    text_column="chosen",
    rejected_text_column="rejected",
    prompt_text_column="prompt",
)

params = LLMTrainingParams(
    model="google/gemma-2-2b",
    data_path="./support_preferences.jsonl",
    project_name="support-bot",

    trainer="orpo",
    dpo_beta=0.15,

    epochs=3,
    batch_size=2,
    gradient_accumulation=4,
    lr=2e-5,

    peft=True,
    lora_r=32,
    lora_alpha=64,

    log="wandb",
)