Instructions to use SonarSource/SonarSweep-java-gpt-oss-20b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SonarSource/SonarSweep-java-gpt-oss-20b with Transformers:

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

pipe = pipeline("text-generation", model="SonarSource/SonarSweep-java-gpt-oss-20b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SonarSource/SonarSweep-java-gpt-oss-20b")
model = AutoModelForCausalLM.from_pretrained("SonarSource/SonarSweep-java-gpt-oss-20b", device_map="auto")
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 SonarSource/SonarSweep-java-gpt-oss-20b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SonarSource/SonarSweep-java-gpt-oss-20b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SonarSource/SonarSweep-java-gpt-oss-20b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SonarSource/SonarSweep-java-gpt-oss-20b

SGLang

How to use SonarSource/SonarSweep-java-gpt-oss-20b 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 "SonarSource/SonarSweep-java-gpt-oss-20b" \
    --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": "SonarSource/SonarSweep-java-gpt-oss-20b",
		"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 "SonarSource/SonarSweep-java-gpt-oss-20b" \
        --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": "SonarSource/SonarSweep-java-gpt-oss-20b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SonarSource/SonarSweep-java-gpt-oss-20b with Docker Model Runner:
```
docker model run hf.co/SonarSource/SonarSweep-java-gpt-oss-20b
```

AbbasSabra commited on Dec 15, 2025

Commit

a9e021e

1 Parent(s): f62a688

Update the model card to refer to the report PDF

Browse files

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -217,6 +217,8 @@ We trained LoRA adapters across all linear layers of the experts and attention b
 ## Evaluation
 ### Code Quality
 We used SonarQube to evaluate the quality, verbosity, and complexity of Java code generated for the [ComplexCodeEval](https://github.com/ComplexCodeEval/ComplexCodeEval) and [MultiPL-E Java](https://huggingface.co/datasets/nuprl/MultiPL-E/viewer/humaneval-java) benchmarks.
@@ -225,7 +227,7 @@ The fine-tuned and base models achieve a similar pass@1 metric for code generati
 The fine-tuned model achieves this metric while generating fewer lines of code.
-For code quality, we see a dramatic reduction in both the number and density of Sonar issues, split among bugs, security vulnerabilities, and code smells (see the [Glossary](#glossary) for definitions).
 | Metric | Base Model | Fine-tuned Model |
 |--------|------------|------------------|

 ## Evaluation
+For a comprehensive analysis with detailed metrics and additional comparisons between the base model and fine-tuned model, see our [detailed evaluation report](https://huggingface.co/SonarSource/SonarSweep-java-gpt-oss-20b/blob/main/report.pdf).
 ### Code Quality
 We used SonarQube to evaluate the quality, verbosity, and complexity of Java code generated for the [ComplexCodeEval](https://github.com/ComplexCodeEval/ComplexCodeEval) and [MultiPL-E Java](https://huggingface.co/datasets/nuprl/MultiPL-E/viewer/humaneval-java) benchmarks.
 The fine-tuned model achieves this metric while generating fewer lines of code.
+For code quality, we see a dramatic reduction in both the number and density of Sonar issues, split among bugs, security vulnerabilities, and code smells (see the [Glossary](#glossary) for definitions). For granular breakdowns by issue type and severity, refer to the [detailed evaluation report](https://huggingface.co/SonarSource/SonarSweep-java-gpt-oss-20b/blob/main/report.pdf).
 | Metric | Base Model | Fine-tuned Model |
 |--------|------------|------------------|