IEEE

Model-Agnostic Empirical Evaluation of Test-Driven Prompt Engineering on Improving Accuracy and Efficiency in Large Language Models Python Code Generation

Abstract: Although Large Language Models (LLMs) are widely adopted for code generation, the generated code can be semantically incorrect, requiring iterations of evaluation and refinement. Test-driven ...
GitHub

Lightning Rod Python SDK

The Lightning Rod SDK provides a simple Python API for generating custom forecasting datasets to train your LLMs. Transform news articles, documents, and other real-world data into high-quality ...
GitHub

GitHub - leeroopedia/workflow-ggml-org-ggml-gpt2-text-generation: GPT-2 text generation inference using GGML model format — Python implementation of the full transformer pipeline

What is this? A complete workflow for generating text with OpenAI's GPT-2 language model using the GGML binary model format. It covers every step from obtaining model weights to producing generated ...
IEEE

A Python Unit Test Generation Method Based on Fine-Tuned Language Models and Coverage

Abstract: Unit testing is fundamental for software reliability, yet manual test construction is inefficient and often results in limited coverage. Existing automated tools struggle with complex ...