Instructions to use wyt2000/CodeV-SVA-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wyt2000/CodeV-SVA-8B with Transformers:

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

pipe = pipeline("text-generation", model="wyt2000/CodeV-SVA-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wyt2000/CodeV-SVA-8B")
model = AutoModelForCausalLM.from_pretrained("wyt2000/CodeV-SVA-8B")
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 Settings

vLLM

How to use wyt2000/CodeV-SVA-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wyt2000/CodeV-SVA-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wyt2000/CodeV-SVA-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wyt2000/CodeV-SVA-8B

SGLang

How to use wyt2000/CodeV-SVA-8B 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 "wyt2000/CodeV-SVA-8B" \
    --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": "wyt2000/CodeV-SVA-8B",
		"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 "wyt2000/CodeV-SVA-8B" \
        --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": "wyt2000/CodeV-SVA-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wyt2000/CodeV-SVA-8B with Docker Model Runner:
```
docker model run hf.co/wyt2000/CodeV-SVA-8B
```

wyt2000 commited on Dec 16, 2025

Commit

56b9fd6

verified ·

1 Parent(s): d76569a

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -12,6 +12,7 @@ license: apache-2.0
 <div align="center">
   <a href="https://huggingface.co/wyt2000/CodeV-SVA-14B"><img src="https://img.shields.io/static/v1?label=Model&message=HuggingFace&color=yellow"></a> &ensp;
 </div>
 ## Introduction
@@ -21,9 +22,9 @@ We introduce CodeV-SVA, a family of large language models designed to translate
 Open-Source Plan:
 - Model ✓
 - Paper
 - Dataset
-- Evaluation code
 - Data synthesis and training code
 ## Evaluation Results
@@ -47,7 +48,7 @@ Open-Source Plan:
 | SVACoder-8B           |    72.0     |     88.8     | <u>90.4</u> |      |    83.5     |    **96.3**    |  **97.2**   |
 | SVACoder-14B          |  **75.8**   |     89.4     | <u>90.4</u> |      |  **84.0**   |  <u>94.9</u>   | <u>95.8</u> |
 ## Models

 <div align="center">
   <a href="https://huggingface.co/wyt2000/CodeV-SVA-14B"><img src="https://img.shields.io/static/v1?label=Model&message=HuggingFace&color=yellow"></a> &ensp;
+  <a href="https://github.com/wyt2000/CodeV-SVA"><img src="https://img.shields.io/static/v1?label=Code&message=Github&color=blue"></a> &ensp;
 </div>
 ## Introduction
 Open-Source Plan:
 - Model ✓
+- Evaluation code ✓
 - Paper
 - Dataset
 - Data synthesis and training code
 ## Evaluation Results
 | SVACoder-8B           |    72.0     |     88.8     | <u>90.4</u> |      |    83.5     |    **96.3**    |  **97.2**   |
 | SVACoder-14B          |  **75.8**   |     89.4     | <u>90.4</u> |      |  **84.0**   |  <u>94.9</u>   | <u>95.8</u> |
+See our GitHub [repo](https://github.com/wyt2000/CodeV-SVA/?tab=readme-ov-file#evaluation) for reproduction.
 ## Models