Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
Python cliconsumer-gpudpofine-tuningggufhuggingfacellmllmopslocal-ailocal-llmloralow-vrammachine-learningollamapeftpythonpytorchqlorasfttransformers
# Soup template: Tool-Calling / Agentic Fine-tuning
# Fine-tune a model to call tools / functions correctly
#
# Data format (JSONL):
# {
# "messages": [{"role": "user", "content": "What's the weather in Tokyo?"}],
# "tools": [{"type": "function", "function": {
# "name": "get_weather",
# "description": "Get current weather for a city",
# "parameters": {"type": "object", "properties": {"city": {"type": "string"}}}
# }}],
# "tool_calls": [{"function": {
# "name": "get_weather",
# "arguments": "{\"city\": \"Tokyo\"}"
# }}]
# }
base: meta-llama/Llama-3.1-8B-Instruct
task: sft
# backend: unsloth # 2-5x faster, pip install "soup-cli[fast]"
data:
train: ./data/tool_calling_train.jsonl
format: tool-calling
val_split: 0.1
max_length: 4096
training:
epochs: 3
lr: 2e-4
batch_size: auto
gradient_accumulation_steps: 4
lora:
r: 16
alpha: 32
target_modules: auto
quantization: 4bit
output: ./output