# Soup template: IPO (Identity Preference Optimization)
# A theoretically grounded variant of DPO with stronger regularization
#
# Data format (JSONL):
#   {"prompt": "What is 2+2?", "chosen": "4", "rejected": "Fish"}

base: meta-llama/Llama-3.1-8B-Instruct
task: ipo
# backend: unsloth  # 2-5x faster, pip install "soup-cli[fast]"

data:
  train: ./data/preference_train.jsonl
  format: dpo
  val_split: 0.1
  max_length: 2048

training:
  epochs: 3
  lr: 1e-5
  batch_size: auto
  gradient_accumulation_steps: 4
  lora:
    r: 64
    alpha: 16
    target_modules: auto
  quantization: 4bit
  ipo_tau: 0.1

output: ./output