Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


CodeV-CL-7B - GGUF
- Model creator: https://huggingface.co/yang-z/
- Original model: https://huggingface.co/yang-z/CodeV-CL-7B/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [CodeV-CL-7B.Q2_K.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.Q2_K.gguf) | Q2_K | 2.36GB |
| [CodeV-CL-7B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.IQ3_XS.gguf) | IQ3_XS | 2.6GB |
| [CodeV-CL-7B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.IQ3_S.gguf) | IQ3_S | 2.75GB |
| [CodeV-CL-7B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.Q3_K_S.gguf) | Q3_K_S | 2.75GB |
| [CodeV-CL-7B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.IQ3_M.gguf) | IQ3_M | 2.9GB |
| [CodeV-CL-7B.Q3_K.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.Q3_K.gguf) | Q3_K | 3.07GB |
| [CodeV-CL-7B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.Q3_K_M.gguf) | Q3_K_M | 3.07GB |
| [CodeV-CL-7B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.Q3_K_L.gguf) | Q3_K_L | 3.35GB |
| [CodeV-CL-7B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.IQ4_XS.gguf) | IQ4_XS | 3.4GB |
| [CodeV-CL-7B.Q4_0.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.Q4_0.gguf) | Q4_0 | 3.56GB |
| [CodeV-CL-7B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.IQ4_NL.gguf) | IQ4_NL | 3.58GB |
| [CodeV-CL-7B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.Q4_K_S.gguf) | Q4_K_S | 3.59GB |
| [CodeV-CL-7B.Q4_K.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.Q4_K.gguf) | Q4_K | 3.8GB |
| [CodeV-CL-7B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.Q4_K_M.gguf) | Q4_K_M | 3.8GB |
| [CodeV-CL-7B.Q4_1.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.Q4_1.gguf) | Q4_1 | 3.95GB |
| [CodeV-CL-7B.Q5_0.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.Q5_0.gguf) | Q5_0 | 4.33GB |
| [CodeV-CL-7B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.Q5_K_S.gguf) | Q5_K_S | 4.33GB |
| [CodeV-CL-7B.Q5_K.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.Q5_K.gguf) | Q5_K | 4.45GB |
| [CodeV-CL-7B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.Q5_K_M.gguf) | Q5_K_M | 4.45GB |
| [CodeV-CL-7B.Q5_1.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.Q5_1.gguf) | Q5_1 | 4.72GB |
| [CodeV-CL-7B.Q6_K.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.Q6_K.gguf) | Q6_K | 5.15GB |
| [CodeV-CL-7B.Q8_0.gguf](https://huggingface.co/RichardErkhov/yang-z_-_CodeV-CL-7B-gguf/blob/main/CodeV-CL-7B.Q8_0.gguf) | Q8_0 | 6.67GB |




Original model description:
---
license: llama2
library_name: transformers
pipeline_tag: text-generation
tags:
  - code
---
<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) | [yang-z/CodeV-DS-6.7B](https://huggingface.co/yang-z/CodeV-DS-6.7B) |
| 7B   | [codellama/CodeLlama-7b-Python-hf](https://huggingface.co/codellama/CodeLlama-7b-Python-hf)         | [yang-z/CodeV-CL-7B](https://huggingface.co/yang-z/CodeV-CL-7B)      |
| 7B   | [Qwen/CodeQwen1.5-7B-Chat](https://huggingface.co/Qwen/CodeQwen1.5-7B-Chat)                         | [yang-z/CodeV-QW-7B](https://huggingface.co/yang-z/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)
```

## Paper
**Arxiv:** <https://arxiv.org/abs/2407.10424>

Please cite the paper if you use the models from CodeV.

```
@misc{yang-z,
      title={CodeV: Empowering LLMs for Verilog Generation through Multi-Level Summarization}, 
      author={Yang Zhao and Di Huang and Chongxiao Li and Pengwei Jin and Ziyuan Nan and Tianyun Ma and Lei Qi and Yansong Pan and Zhenxing Zhang and Rui Zhang and Xishan Zhang and Zidong Du and Qi Guo and Xing Hu and Yunji Chen},
      year={2024},
      eprint={2407.10424},
      archivePrefix={arXiv},
      primaryClass={cs.PL},
      url={https://arxiv.org/abs/2407.10424}, 
}
```

## 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