Skip to content

armgit / Soup

Public Imported from GitHub
0

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

398 B
Raw Blame
# Soup template: Chat Assistant
# Fine-tune a model for conversational chat
# Usage: soup init --template chat

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

data:
  train: ./data/train.jsonl
  format: alpaca
  val_split: 0.1
  max_length: 2048

training:
  epochs: 3
  lr: 2e-5
  batch_size: auto
  lora:
    r: 64
    alpha: 16
    target_modules: auto
  quantization: 4bit

output: ./output