LLM-Finetuning-Lab/Makefile at master · Synthora-AI/LLM-Finetuning-Lab · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
# Makefile for LLM Fine-Tuning Lab

.PHONY: help install dev-install clean test lint format docker-build docker-run

help: ## Show this help message
	@echo 'Usage: make [target]'
	@echo ''
	@echo 'Available targets:'
	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf "  \033[36m%-20s\033[0m %s\n", $$1, $$2}'

install: ## Install dependencies
	pip install -r requirements.txt
	pip install -e .

dev-install: ## Install development dependencies
	pip install -r requirements.txt
	pip install -e ".[dev]"
	pip install black flake8 isort mypy pytest pytest-cov

clean: ## Clean build artifacts and caches
	rm -rf build/
	rm -rf dist/
	rm -rf *.egg-info
	find . -type d -name __pycache__ -exec rm -rf {} +
	find . -type f -name '*.pyc' -delete
	find . -type f -name '*.pyo' -delete

test: ## Run tests
	pytest tests/ -v --cov=src --cov-report=html --cov-report=term

lint: ## Run linters
	black --check src/ scripts/
	flake8 src/ scripts/ --max-line-length=120
	isort --check-only src/ scripts/
	mypy src/

format: ## Format code
	black src/ scripts/
	isort src/ scripts/

docker-build: ## Build Docker image
	docker-compose build

docker-run: ## Run Docker containers
	docker-compose up -d

docker-stop: ## Stop Docker containers
	docker-compose down

docker-logs: ## View Docker logs
	docker-compose logs -f

train-summarizer: ## Train summarization model
	python scripts/train_summarizer.py \
		--config configs/summarization.yaml \
		--data datasets/processed/gov_articles.json \
		--output checkpoints/summarizer-v1

train-classifier: ## Train classification model
	python scripts/train_classifier.py \
		--config configs/classification.yaml \
		--data datasets/processed/labeled_articles.json \
		--output checkpoints/classifier-v1

prepare-data: ## Prepare training data from SynthoraAI
	python scripts/prepare_data.py \
		--task summarization \
		--limit 5000 \
		--output datasets/processed/gov_articles.json

evaluate: ## Evaluate model
	python scripts/evaluate.py \
		--model checkpoints/summarizer-v1 \
		--test-data datasets/processed/test.json \
		--task summarization

export-model: ## Export model for production
	python scripts/export.py \
		--model checkpoints/summarizer-v1 \
		--output exports/summarizer \
		--format onnx \
		--quantize

jupyter: ## Start Jupyter Lab
	jupyter lab --ip=0.0.0.0 --port=8888 --no-browser

tensorboard: ## Start TensorBoard
	tensorboard --logdir=runs --port=6006

setup: install ## Initial setup
	mkdir -p checkpoints datasets logs outputs runs
	cp .env.example .env
	@echo "Setup complete! Edit .env with your API keys."