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.

440 B
Raw Blame
# Soup template: Code Model
# Fine-tune a model for code generation / completion

base: codellama/CodeLlama-7b-Instruct-hf
task: sft
# backend: unsloth  # 2-5x faster, pip install "soup-cli[fast]"

data:
  train: ./data/code_train.jsonl
  format: alpaca
  val_split: 0.1
  max_length: 4096

training:
  epochs: 2
  lr: 1e-5
  batch_size: auto
  lora:
    r: 128
    alpha: 32
    target_modules: auto
  quantization: 4bit

output: ./output