---
license: apache-2.0
---
<div align="center">
  <img src="./assets/logo.png" style="zoom:25%;" /> 
</div>

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

<img src="assets/overview.png" style="zoom:50%;" /> 

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](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base) | [[zyyy1023399127/CodeV-DS-6.7B](https://huggingface.co/zyyy1023399127/CodeV-DS-6.7B) |
| 7B   | [codellama/CodeLlama-7b-Python-hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf)         | [zyyy1023399127/CodeV-CL-7B](https://huggingface.co/zyyy1023399127/CodeV-CL-7B)      |
| 7B   | [Qwen/CodeQwen1.5-7B-Chat](https://huggingface.co/Qwen/CodeQwen1.5-7B-Chat)                         | [zyyy1023399127/CodeV-QW-7B](https://huggingface.co/zyyy1023399127/CodeV-QW-7B)      |

## Test

If you want to test the generation capability of existing models on Verilog, you need to install the [VerilogEval](https://github.com/NVlabs/verilog-eval) and [RTLLM](https://github.com/hkust-zhiyao/rtllm) environments.

## Quick Start

```python
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](https://github.com/ise-uiuc/magicoder): Training code, original datasets and data decontamination
* [DeepSeek-Coder](https://github.com/deepseek-ai/DeepSeek-Coder): Base model for CodeV-DeepSeek
* [CodeLlama](https://ai.meta.com/research/publications/code-llama-open-foundation-models-for-code/): Base model for CodeLlama
* [CodeQwen](https://github.com/QwenLM/CodeQwen1.5): CodeV-CodeQwen