# Soup template: Medical / Domain Expert
# Fine-tune a model with domain-specific knowledge
# Usage: soup init --template medical

base: meta-llama/Llama-3.1-8B-Instruct
task: sft

data:
  train: ./data/medical_train.jsonl
  format: alpaca
  val_split: 0.15
  max_length: 2048

training:
  epochs: 5
  lr: 1e-5
  batch_size: auto
  gradient_accumulation_steps: 8
  lora:
    r: 128
    alpha: 32
    target_modules: auto
  quantization: 4bit

output: ./output