Instructions to use kusonooyasumi/xss-strix-8b-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kusonooyasumi/xss-strix-8b-sft with Transformers:

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

pipe = pipeline("text-generation", model="kusonooyasumi/xss-strix-8b-sft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("kusonooyasumi/xss-strix-8b-sft")
model = AutoModelForMultimodalLM.from_pretrained("kusonooyasumi/xss-strix-8b-sft")
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 kusonooyasumi/xss-strix-8b-sft with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/kusonooyasumi/xss-strix-8b-sft

SGLang

How to use kusonooyasumi/xss-strix-8b-sft 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 "kusonooyasumi/xss-strix-8b-sft" \
    --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": "kusonooyasumi/xss-strix-8b-sft",
		"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 "kusonooyasumi/xss-strix-8b-sft" \
        --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": "kusonooyasumi/xss-strix-8b-sft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use kusonooyasumi/xss-strix-8b-sft with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for kusonooyasumi/xss-strix-8b-sft to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for kusonooyasumi/xss-strix-8b-sft to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for kusonooyasumi/xss-strix-8b-sft to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="kusonooyasumi/xss-strix-8b-sft",
    max_seq_length=2048,
)

Docker Model Runner
How to use kusonooyasumi/xss-strix-8b-sft with Docker Model Runner:
```
docker model run hf.co/kusonooyasumi/xss-strix-8b-sft
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

xss-strix-8b

Fine-tuned Qwen3-8B model specialized for XSS vulnerability detection as part of the Strix security agent framework.

Model Description

This model has been fine-tuned on 1,1k examples of multi-turn security testing conversations, teaching it to:

Use Strix agent tools (browser_action, python_action, terminal, etc.)
Reason through XSS vulnerability testing with <think> blocks
Generate proper XML tool call syntax
Follow systematic vulnerability hunting methodologies

Training Details

Base Model: Qwen/Qwen3-8B
Fine-tuning Method: QLoRA (4-bit quantization + LoRA)
LoRA Rank: N/A
LoRA Alpha: N/A
Epochs: N/A
Learning Rate: N/A
Training Examples: N/A
Final Loss: 0.0000

Usage

With Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("kusonooyasumi/xss-strix-8b")
tokenizer = AutoTokenizer.from_pretrained("kusonooyasumi/xss-strix-8b")

messages = [
    {"role": "system", "content": "You are a Strix security agent..."},
    {"role": "user", "content": "<agent_delegation>Test for XSS...</agent_delegation>"}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(tokenizer.decode(outputs[0]))

With Ollama (GGUF)

# Download the GGUF
ollama create xss-strix -f Modelfile

# Or manually with llama.cpp
./main -m xss-strix-8b-Q4_K_M.gguf -p "<|im_start|>system\nYou are a Strix security agent..."

Recommended System Prompt

You are a Strix security agent. Reason in <think> blocks, act via tools.
Work autonomously. Never ask for permission. Be relentless and thorough.

Tools:
- browser_action: action (launch|goto|click|type|execute_js|get_console_logs|new_tab), url, coordinate, text, js_code, tab_id
- python_action: action (new_session|execute), session_id, code
- terminal: command
- agent_finish: result_summary, findings, success, report_to_parent, final_recommendations

Format: <function=name>
<parameter=param>value</parameter>
</function>

Limitations

Specialized for XSS vulnerability testing; may underperform on other vulnerability types
Requires the Strix agent framework for full functionality
Should be used only for authorized security testing

License

Apache 2.0 (following base model license)

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for kusonooyasumi/xss-strix-8b-sft

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Finetuned

(1682)

this model

Quantizations

2 models