Instructions to use yang-z/CodeV-CL-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yang-z/CodeV-CL-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="yang-z/CodeV-CL-7B")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("yang-z/CodeV-CL-7B") model = AutoModelForCausalLM.from_pretrained("yang-z/CodeV-CL-7B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use yang-z/CodeV-CL-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "yang-z/CodeV-CL-7B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "yang-z/CodeV-CL-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/yang-z/CodeV-CL-7B
- SGLang
How to use yang-z/CodeV-CL-7B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "yang-z/CodeV-CL-7B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "yang-z/CodeV-CL-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "yang-z/CodeV-CL-7B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "yang-z/CodeV-CL-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use yang-z/CodeV-CL-7B with Docker Model Runner:
docker model run hf.co/yang-z/CodeV-CL-7B
Update README.md
Browse files
README.md
CHANGED
|
@@ -61,6 +61,23 @@ response = result[0]["generated_text"]
|
|
| 61 |
print("Response:", response)
|
| 62 |
```
|
| 63 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
## Acknowledgements
|
| 65 |
|
| 66 |
* [Magicoder](https://github.com/ise-uiuc/magicoder): Training code, original datasets and data decontamination
|
|
|
|
| 61 |
print("Response:", response)
|
| 62 |
```
|
| 63 |
|
| 64 |
+
## Paper
|
| 65 |
+
**Arxiv:** <https://arxiv.org/abs/2407.10424>
|
| 66 |
+
|
| 67 |
+
Please cite the paper if you use the models from CodeV.
|
| 68 |
+
|
| 69 |
+
```
|
| 70 |
+
@misc{yang-z,
|
| 71 |
+
title={CodeV: Empowering LLMs for Verilog Generation through Multi-Level Summarization},
|
| 72 |
+
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},
|
| 73 |
+
year={2024},
|
| 74 |
+
eprint={2407.10424},
|
| 75 |
+
archivePrefix={arXiv},
|
| 76 |
+
primaryClass={cs.PL},
|
| 77 |
+
url={https://arxiv.org/abs/2407.10424},
|
| 78 |
+
}
|
| 79 |
+
```
|
| 80 |
+
|
| 81 |
## Acknowledgements
|
| 82 |
|
| 83 |
* [Magicoder](https://github.com/ise-uiuc/magicoder): Training code, original datasets and data decontamination
|