Instructions to use athena129/CyberSecQwen-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use athena129/CyberSecQwen-4B with Transformers:

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

pipe = pipeline("text-generation", model="athena129/CyberSecQwen-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("athena129/CyberSecQwen-4B")
model = AutoModelForCausalLM.from_pretrained("athena129/CyberSecQwen-4B")
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]:]))

PEFT
How to use athena129/CyberSecQwen-4B with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use athena129/CyberSecQwen-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "athena129/CyberSecQwen-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "athena129/CyberSecQwen-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/athena129/CyberSecQwen-4B

SGLang

How to use athena129/CyberSecQwen-4B 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 "athena129/CyberSecQwen-4B" \
    --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": "athena129/CyberSecQwen-4B",
		"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 "athena129/CyberSecQwen-4B" \
        --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": "athena129/CyberSecQwen-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use athena129/CyberSecQwen-4B with Docker Model Runner:
```
docker model run hf.co/athena129/CyberSecQwen-4B
```

athena129 commited on 14 days ago

Commit

a3f982b

verified ·

1 Parent(s): 7ddb714

Remove emoji from headline result table

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -216,7 +216,7 @@ Evaluated under the [Foundation-Sec-8B protocol (arXiv:2504.21039 §B.3-B.4)](ht
 | Benchmark | Metric | CyberSecQwen-4B | Foundation-Sec-Instruct-8B | Δ |
 |---|---|---:|---:|---:|
-| **CTI-MCQ** (2,500 items) | strict_acc, 5-trial mean ± std | **0.5868 ± 0.0029** | 0.4996 | **+8.7 pp ✅** |
 | **CTI-RCM** (1,000 items) | strict_acc, 5-trial mean ± std | **0.6664 ± 0.0023** | 0.6850 | -1.9 pp |
 Parseable rates were 100% on CTI-RCM and 98.1% on CTI-MCQ — the model produces well-formed outputs in the expected response convention.

 | Benchmark | Metric | CyberSecQwen-4B | Foundation-Sec-Instruct-8B | Δ |
 |---|---|---:|---:|---:|
+| **CTI-MCQ** (2,500 items) | strict_acc, 5-trial mean ± std | **0.5868 ± 0.0029** | 0.4996 | **+8.7 pp** |
 | **CTI-RCM** (1,000 items) | strict_acc, 5-trial mean ± std | **0.6664 ± 0.0023** | 0.6850 | -1.9 pp |
 Parseable rates were 100% on CTI-RCM and 98.1% on CTI-MCQ — the model produces well-formed outputs in the expected response convention.