README.md

metadata

title: Unit Test Generator
emoji: 🌖
colorFrom: indigo
colorTo: purple
sdk: docker
sdk_version: 6.3.0
app_file: app.py
pinned: false
license: openrail
short_description: Fine-tuned Llama-3 for generating Python unit tests

🧪 AI Unit Test Generator

A Fine-Tuned Llama-3 Model for Automated QA

This application uses a custom fine-tuned version of Meta's Llama-3-8B to automatically generate pytest unit tests for Python functions.

🚀 How it Works

1. Paste your Python function into the box.
2. Click Generate.
3. The model produces a complete, runnable pytest test case.

⚙️ Technical Architecture

To run a robust LLM on the free CPU tier, this project uses a split-architecture approach:

• Model: Llama-3-8B fine-tuned on the Alpaca-Python-18k dataset.
• Quantization: The model weights were converted to GGUF (Q4_K_M) format to reduce RAM usage from 16GB to ~5GB.
• Inference: Running locally on CPU using llama-cpp-python.
• Weights: Hosted separately in the Model Repository.

---

Built by Nihar Donthireddy Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference