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

d76569a

verified ·

1 Parent(s): f3b6da4

Update README.md

Browse files

Files changed (1) hide show

README.md +23 -1

README.md CHANGED Viewed

@@ -26,6 +26,29 @@ Open-Source Plan:
 - Evaluation code
 - Data synthesis and training code
 ## Models
 | Model | Download |
@@ -34,7 +57,6 @@ Open-Source Plan:
 |    CodeV-SVA-no-think-8B     |   [🤗HuggingFace](https://huggingface.co/wyt2000/CodeV-SVA-no-think-8B)    |
 |    CodeV-SVA-14B     |   [🤗HuggingFace](https://huggingface.co/wyt2000/CodeV-SVA-14B)    |
 ## Usage
 ````python

 - Evaluation code
 - Data synthesis and training code
+## Evaluation Results
+| Model                 |             | NL2SVA-Human |             |      |             | NL2SVA-Machine |             |
+| :-------------------- | :---------: | :----------: | :---------: | ---- | :---------: | :------------: | :---------: |
+|                       |   Func.@1   |   Func.@16   |  Func.@32   |      |   Func.@1   |    Func.@16    |  Func.@32   |
+|                       |             |              |             |      |             |                |             |
+| DeepSeek-R1-671B      | <u>74.6</u> |   **90.3**   | <u>90.4</u> |      |    81.0     |      93.3      |    94.3     |
+| GPT-5                 |    71.8     | <u>90.2</u>  |  **92.7**   |      |    81.8     |      93.2      |    94.3     |
+| DeepSeek-V3.1-671B    |    63.1     |     81.4     |    84.9     |      | <u>83.8</u> |      92.9      |    93.6     |
+| GPT-4o                |    64.1     |     75.2     |    78.1     |      |    68.5     |      81.3      |    83.7     |
+|                       |             |              |             |      |             |                |             |
+| RTLCoder-DS-v1.1-6.7B |    25.9     |     58.8     |    65.8     |      |    21.7     |      54.8      |    60.8     |
+| CodeV-R1-Qwen-7B      |    25.2     |     55.8     |    61.6     |      |    37.4     |      76.6      |    83.0     |
+|                       |             |              |             |      |             |                |             |
+| Qwen3-8B              |    32.3     |     71.6     |    74.0     |      |    46.1     |      88.0      |    90.5     |
+| Qwen3-14B             |    61.6     |     86.1     |    87.7     |      |    75.3     |      92.7      |    94.3     |
+|                       |             |              |             |      |             |                |             |
+| SVACoder-no-think-8B  |    65.8     |     84.4     |    86.3     |      |    78.7     |      90.9      |    91.9     |
+| 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
 | Model | Download |
 |    CodeV-SVA-no-think-8B     |   [🤗HuggingFace](https://huggingface.co/wyt2000/CodeV-SVA-no-think-8B)    |
 |    CodeV-SVA-14B     |   [🤗HuggingFace](https://huggingface.co/wyt2000/CodeV-SVA-14B)    |
 ## Usage
 ````python