GitHub - RashenThemiya/ai-model: This study evaluates the effectiveness of using Large Language Models (LLMs) for automated JavaScript unit test generation. Specifically, it compares the performance of the state-of-the-art GPT-4 model with a fine-tuned version of the open-source CodeT5p model.

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 2 Commits
.gitignore		.gitignore
20APSE4848_SE6108(2020-21).pdf		20APSE4848_SE6108(2020-21).pdf
GPT4_JS_Test_Case_Research_Paper.docx		GPT4_JS_Test_Case_Research_Paper.docx
app.py		app.py
model.ipynb		model.ipynb
readme.txt		readme.txt
requir		requir
requirements.txt		requirements.txt

Repository files navigation

js-test-generator-model-https://drive.google.com/drive/folders/1sv1Dv50X6lF9d2nsNMHDIMs_gps_HJ0-?usp=sharing

curl -X POST http://127.0.0.1:5000/generate \
  -H "Content-Type: application/json" \
  -d "{\"code\": \"function add(a, b) { return a + b; }\"}"

{
  "code": "function factorial(n) { if (n === 0) return 1; return n * factorial(n - 1); }"
}

About

This study evaluates the effectiveness of using Large Language Models (LLMs) for automated JavaScript unit test generation. Specifically, it compares the performance of the state-of-the-art GPT-4 model with a fine-tuned version of the open-source CodeT5p model.

Readme