PyraNet: A Multi-Layered Hierarchical Dataset for Verilog
This addresses the need for better Verilog code generation tools for hardware design engineers, though it appears incremental as it builds on existing LLM fine-tuning approaches.
The paper tackles the problem of poor quality in Large Language Model-generated Verilog code by introducing PyraNet, a novel open-source dataset and fine-tuning technique, resulting in improvements of up to 32.6% over baseline models and 16.7% over state-of-the-art models.
Recently, there has been a growing interest in leveraging Large Language Models for Verilog code generation. However, the current quality of the generated Verilog code remains suboptimal. This is largely due to the absence of well-defined, well-organized datasets with high-quality samples, as well as a lack of innovative fine-tuning methods and models specifically trained on Verilog. In this paper, we introduce a novel open-source dataset and a corresponding fine-tuning technique, which utilizes a multi-layered structure that we refer to as PyraNet. Our experiments demonstrate that employing the proposed dataset and fine-tuning approach leads to a more accurate fine-tuned model, producing syntactically and functionally correct Verilog code. The evaluation results show improvements by up-to $32.6\%$ in comparison to the CodeLlama-7B baseline model and up-to $16.7\%$ in comparison to the state-of-the-art models using VerilogEval evaluation platform.