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: Audio / Speech
# Fine-tune an audio-language model for speech understanding
#
# Supported models: Qwen2-Audio, Whisper (via transformers)
#
# Data format (JSONL):
# {"audio": "path/to/audio.wav", "messages": [
# {"role": "user", "content": "Transcribe."},
# {"role": "assistant", "content": "Hello world."}]}
base: Qwen/Qwen2-Audio-7B-Instruct
task: sft
modality: audio
backend: transformers # The audio SFT path does not use Unsloth.
data:
train: ./data/audio_train.jsonl
format: audio
audio_dir: ./data/audio
val_split: 0.1
max_length: 2048
training:
epochs: 3
lr: 1e-5
batch_size: auto
gradient_accumulation_steps: 8
lora:
r: 64
alpha: 16
target_modules: auto
quantization: 4bit
output: ./output_audio