CodeV:Empowering LLMs for Verilog Generation through Multi-Level Summarization

CodeV is an innovative series of open-source, instruction-tuned Large Language Models (LLMs) specifically designed for the generation of high-quality Verilog code, addressing the challenges faced by existing models in this domain. (This repo is under development)

Models and Datasets

	Base Model	CodeV
6.7B	deepseek-ai/deepseek-coder-6.7b-base	zyyy1023399127/CodeV-DS-6.7B
7B	codellama/CodeLlama-7b-Python-hf	zyyy1023399127/CodeV-CL-7B
7B	Qwen/CodeQwen1.5-7B-Chat	zyyy1023399127/CodeV-QW-7B

Test

If you want to test the generation capability of existing models on Verilog, you need to install the VerilogEval and RTLLM environments.

Quick Start

from transformers import pipeline

import torch



prompt= "FILL IN THE QUESTION"



generator = pipeline(

  model="CODEV",

  task="text-generation",

  torch_dtype=torch.bfloat16,

  device_map="auto",

)



result = generator(prompt , max_length=2048, num_return_sequences=1, temperature=0.0)

response = result[0]["generated_text"]

print("Response:", response)

Acknowledgements

Magicoder: Training code, original datasets and data decontamination
DeepSeek-Coder: Base model for CodeV-DeepSeek
CodeLlama: Base model for CodeLlama
CodeQwen: CodeV-CodeQwen