# Install Python 3.12 if needed
brew install python@3.12

# Create venv
python3.12 -m venv .venv
source .venv/bin/activate

# Verify arm64 (must show arm64, not x86_64)
python -c "import platform; print(platform.machine())"

# Install PyTorch
pip install torch torchaudio

# Clone and install
git clone https://github.com/mattmireles/gemma-tuner-multimodal
cd gemma-tuner-multimodal
pip install -e .

# For Gemma 4 support (separate venv recommended)
pip install -r requirements/requirements-gemma4.txt

huggingface-cli login
# Or set environment variable:
export HF_TOKEN=your_token_here

# Check system is ready
gemma-macos-tuner system-check

# Guided setup wizard (recommended for first run)
gemma-macos-tuner wizard

# Prepare dataset
gemma-macos-tuner prepare <dataset-profile>

# Fine-tune a model
gemma-macos-tuner finetune <profile> --json-logging

# Evaluate a run
gemma-macos-tuner evaluate <profile-or-run>

# Export merged HF/SafeTensors (merges LoRA when adapter_config.json present)
gemma-macos-tuner export <run-dir-or-profile>

# Blacklist bad samples from errors
gemma-macos-tuner blacklist <profile>

# List training runs
gemma-macos-tuner runs list

[defaults]
output_dir = output
batch_size = 2
gradient_accumulation_steps = 8
learning_rate = 2e-4
num_train_epochs = 3

[model:gemma-3n-e2b-it]
group = gemma
base_model = google/gemma-3n-E2B-it

[model:gemma-4-e2b-it]
group = gemma
base_model = google/gemma-4-E2B-it

[dataset:my-audio-dataset]
data_dir = data/datasets/my-audio-dataset
audio_column = audio_path
text_column = transcript

[profile:my-audio-profile]
model = gemma-3n-e2b-it
dataset = my-audio-dataset
modality = audio
lora_r = 16
lora_alpha = 32
lora_dropout = 0.05
max_seq_length = 512

export GEMMA_TUNER_CONFIG=/path/to/my/config.ini

[profile:text-instruction]
model = gemma-3n-e2b-it
dataset = my-text-dataset
modality = text
text_sub_mode = instruction
prompt_column = prompt
text_column = response
max_seq_length = 2048
lora_r = 16
lora_alpha = 32

[profile:text-completion]
model = gemma-3n-e2b-it
dataset = my-text-dataset
modality = text
text_sub_mode = completion
text_column = text
max_seq_length = 2048

prompt,response
"What is photosynthesis?","Photosynthesis is the process by which plants..."
"Explain LoRA fine-tuning","LoRA (Low-Rank Adaptation) is a parameter-efficient..."

[profile:image-caption]
model = gemma-3n-e2b-it
dataset = my-image-dataset
modality = image
image_sub_mode = captioning
image_token_budget = 256
prompt_column = prompt
text_column = caption
max_seq_length = 512

image_path,prompt,caption
/data/images/img1.jpg,Describe this image,A dog sitting on a green lawn...
/data/images/img2.jpg,What is shown here,A bar chart showing quarterly revenue...

[profile:audio-asr]
model = gemma-3n-e2b-it
dataset = my-audio-dataset
modality = audio
audio_column = audio_path
text_column = transcript
max_seq_length = 512
lora_r = 16
lora_alpha = 32
lora_dropout = 0.05

audio_path,transcript
/data/audio/recording1.wav,The patient presents with acute respiratory symptoms
/data/audio/recording2.wav,Counsel objects to the characterization of the evidence

data/
└── datasets/
    └── <dataset-name>/
        ├── train.csv       # required
        ├── validation.csv  # optional
        └── test.csv        # optional

output/
└── {run-id}-{profile}/
    ├── metadata.json
    ├── metrics.json
    ├── checkpoint-*/
    └── adapter_model/      # LoRA artifacts

from gemma_tuner.core.config import load_config
from gemma_tuner.core.ops import run_finetune

# Load config
config = load_config("config/config.ini")

# Run fine-tuning for a profile
run_finetune(profile="my-audio-profile", config=config, json_logging=True)

from gemma_tuner.utils.device import get_device, memory_hint

device = get_device()   # Returns "mps", "cuda", or "cpu"
print(f"Training on: {device}")

hint = memory_hint(model_key="gemma-3n-e2b-it")
print(hint)

from gemma_tuner.utils.dataset_utils import load_csv_dataset

train_df, val_df = load_csv_dataset(
    data_dir="data/datasets/my-text-dataset",
    text_column="response",
    prompt_column="prompt"
)
print(f"Train samples: {len(train_df)}, Val samples: {len(val_df)}")

from peft import LoraConfig, get_peft_model
from transformers import AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained(
    "google/gemma-3n-E2B-it",
    torch_dtype="auto",
    device_map="mps"
)

lora_config = LoraConfig(
    r=16,
    lora_alpha=32,
    lora_dropout=0.05,
    target_modules=["q_proj", "v_proj", "k_proj", "o_proj"],
    task_type="CAUSAL_LM"
)

model = get_peft_model(model, lora_config)
model.print_trainable_parameters()

# 1. Prepare your data
mkdir -p data/datasets/my-dataset
cp train.csv data/datasets/my-dataset/
cp validation.csv data/datasets/my-dataset/

# 2. Add profile to config/config.ini
cat >> config/config.ini << 'EOF'
[dataset:my-dataset]
data_dir = data/datasets/my-dataset

[profile:my-text-run]
model = gemma-3n-e2b-it
dataset = my-dataset
modality = text
text_sub_mode = instruction
prompt_column = prompt
text_column = response
max_seq_length = 2048
lora_r = 16
lora_alpha = 32
EOF

# 3. Prepare dataset
gemma-macos-tuner prepare my-dataset

# 4. Fine-tune
gemma-macos-tuner finetune my-text-run --json-logging

# 5. Export merged weights
gemma-macos-tuner export my-text-run

[dataset:large-audio-gcs]
source = gcs
gcs_bucket = my-bucket
gcs_prefix = audio-training-data/
audio_column = audio_path
text_column = transcript

[profile:large-audio-run]
model = gemma-3n-e4b-it
dataset = large-audio-gcs
modality = audio
lora_r = 32
lora_alpha = 64

export GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json
gemma-macos-tuner finetune large-audio-run

[model:my-custom-gemma]
group = gemma
base_model = my-org/my-gemma-checkpoint

[profile:custom-run]
model = my-custom-gemma
dataset = my-dataset
modality = text
text_sub_mode = instruction

python -c "import platform; print(platform.machine())"
# Must be arm64 — if x86_64, reinstall Python natively:
brew install python@3.12
python3.12 -m venv .venv && source .venv/bin/activate

# Gemma 4 requires the updated Transformers stack
pip install -r requirements/requirements-gemma4.txt
# Use a separate venv if you also need Gemma 3n

export GEMMA_TUNER_CONFIG=/absolute/path/to/config/config.ini
gemma-macos-tuner finetune my-profile

huggingface-cli login
# Or:
export HF_TOKEN=your_hf_token
# Accept Gemma license at: https://huggingface.co/google/gemma-3n-E2B-it

gemma-macos-tuner system-check