Instructions to use yang-z/CodeV-QW-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yang-z/CodeV-QW-7B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="yang-z/CodeV-QW-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yang-z/CodeV-QW-7B")
model = AutoModelForCausalLM.from_pretrained("yang-z/CodeV-QW-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use yang-z/CodeV-QW-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-QW-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yang-z/CodeV-QW-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yang-z/CodeV-QW-7B

SGLang

How to use yang-z/CodeV-QW-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-QW-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yang-z/CodeV-QW-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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-QW-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yang-z/CodeV-QW-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yang-z/CodeV-QW-7B with Docker Model Runner:
```
docker model run hf.co/yang-z/CodeV-QW-7B
```

Improve model card - Add pipeline tag, library name, link Github repository and project page

by nielsr HF Staff - opened Jun 4, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-16

Files changed (1) hide show

README.md +9 -16

README.md CHANGED Viewed

@@ -1,13 +1,16 @@
 ---
-license: apache-2.0
 language:
 - en
 metrics:
 - accuracy
 tags:
 - code
 arxiv: 2407.10424
 ---
 <div align="center">
   <img src="./assets/logo.png" style="zoom:25%;" />
 </div>
@@ -18,7 +21,6 @@ arxiv: 2407.10424
 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                                                                                |
@@ -38,35 +40,26 @@ 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.
 ```
@@ -85,4 +78,4 @@ Please cite the paper if you use the models from CodeV.
 * [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

 ---
 language:
 - en
+license: apache-2.0
 metrics:
 - accuracy
 tags:
 - code
 arxiv: 2407.10424
+library_name: transformers
+pipeline_tag: text-generation
 ---
 <div align="center">
   <img src="./assets/logo.png" style="zoom:25%;" />
 </div>
 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                                                                                |
 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>
+Project page: https://iprc-dip.github.io/CodeV-R1
+Code: https://github.com/iprc-dip/CodeV
 Please cite the paper if you use the models from CodeV.
 ```
 * [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