Instructions to use ree2raz/CyberSecQwen-4B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ree2raz/CyberSecQwen-4B-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="ree2raz/CyberSecQwen-4B-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ree2raz/CyberSecQwen-4B-AWQ")
model = AutoModelForCausalLM.from_pretrained("ree2raz/CyberSecQwen-4B-AWQ")
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 ree2raz/CyberSecQwen-4B-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ree2raz/CyberSecQwen-4B-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ree2raz/CyberSecQwen-4B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ree2raz/CyberSecQwen-4B-AWQ

SGLang

How to use ree2raz/CyberSecQwen-4B-AWQ 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 "ree2raz/CyberSecQwen-4B-AWQ" \
    --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": "ree2raz/CyberSecQwen-4B-AWQ",
		"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 "ree2raz/CyberSecQwen-4B-AWQ" \
        --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": "ree2raz/CyberSecQwen-4B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ree2raz/CyberSecQwen-4B-AWQ with Docker Model Runner:
```
docker model run hf.co/ree2raz/CyberSecQwen-4B-AWQ
```

ree2raz commited on 10 days ago

Commit

cbb2ea7

verified ·

1 Parent(s): 955f967

Add CTI-Bench evaluation results (AWQ 4-bit vs FP16)

Browse files

Files changed (1) hide show

README.md +94 -0

README.md ADDED Viewed

	@@ -0,0 +1,94 @@

+---
+license: apache-2.0
+tags:
+- qwen3
+- cybersecurity
+- cti
+- cwe-classification
+- vulnerability-analysis
+- awq
+- 4-bit
+- quantized
+library_name: transformers
+pipeline_tag: text-generation
+---
+# CyberSecQwen-4B-AWQ
+4-bit AWQ quantized version of [CyberSecQwen-4B](https://huggingface.co/lablab-ai-amd-developer-hackathon/CyberSecQwen-4B).
+## Quantization
+| Parameter | Value |
+|---|---|
+| Method | AWQ (group_size=128, zero_point=True) |
+| Weight precision | 4-bit |
+| Compute dtype | float16 |
+| Calibration samples | 128 CTI-Bench prompts |
+| Quantization tool | autoawq |
+| Calibration hardware | Modal A100 |
+## CTI-Bench Evaluation
+Evaluated under the [Foundation-Sec-8B protocol](https://arxiv.org/abs/2504.21039) (arXiv:2504.21039):
+- Temperature 0.3, max_tokens 512, concurrency 32
+- 5 independent trials, zero-shot (no system prompt)
+- vLLM v0.20.1 with awq_marlin kernel on Modal L4 GPU
+| Task | AWQ 4-bit | FP16 Reference | Delta |
+|---|---|---|---|
+| CTI-MCQ (2,500 items) | 0.5921 +/- 0.0083 | 0.5868 +/- 0.0029 | +0.0053 |
+| CTI-RCM (1,000 items) | 0.5558 +/- 0.0040 | 0.6664 +/- 0.0023 | -0.1106 |
+**Key findings:**
+- **CTI-MCQ**: AWQ 4-bit matches or slightly exceeds FP16 performance (+0.5 points). No measurable accuracy loss.
+- **CTI-RCM**: AWQ 4-bit degrades by 0.1 points vs FP16. Parseable rate > 99.8% so answer extraction is working correctly. The model retains correct CWE identification in reasoning but sometimes diverges on final answers. This gap can likely be reduced with more calibration data.
+## Trial results
+### CTI-MCQ
+| Trial | Seed | Accuracy |
+|---|---|---|
+| 1 | 42 | 0.6016 |
+| 2 | 43 | 0.5984 |
+| 3 | 44 | 0.5936 |
+| 4 | 45 | 0.5780 |
+| 5 | 46 | 0.5888 |
+### CTI-RCM
+| Trial | Seed | Accuracy |
+|---|---|
+| 1 | 42 | 0.5520 |
+| 2 | 43 | 0.5500 |
+| 3 | 44 | 0.5600 |
+| 4 | 45 | 0.5580 |
+| 5 | 46 | 0.5590 |
+## Usage with vLLM
+```bash
+vllm serve ree2raz/CyberSecQwen-4B-AWQ --quantization awq_marlin --dtype float16
+```
+## Model Size
+| Format | Size |
+|---|---|
+| Original FP16 | ~8 GB |
+| AWQ 4-bit | ~2.7 GB |
+## Citation
+```bibtex
+@misc{cybersecqwen2026,
+  title  = {CyberSecQwen-4B: A Compact CTI Specialist Fine-Tuned from Qwen3-4B-Instruct-2507 on AMD MI300X},
+  author = {Mulia, Samuel},
+  year   = {2026},
+  publisher = {Hugging Face},
+  url    = {https://huggingface.co/athena129/CyberSecQwen-4B}
+}
+```
+## Evaluation Infrastructure
+[GitHub repository](https://github.com/ree2raz/cyberSecQwen_4b_4bit) — Modal scripts for AWQ quantization + vLLM CTI-Bench evaluation.