Instructions to use alirezaaminzadeh/soc-analyst-tool-use with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alirezaaminzadeh/soc-analyst-tool-use with Transformers:

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

pipe = pipeline("text-generation", model="alirezaaminzadeh/soc-analyst-tool-use")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("alirezaaminzadeh/soc-analyst-tool-use", device_map="auto")

PEFT
How to use alirezaaminzadeh/soc-analyst-tool-use with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alirezaaminzadeh/soc-analyst-tool-use with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alirezaaminzadeh/soc-analyst-tool-use"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alirezaaminzadeh/soc-analyst-tool-use",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/alirezaaminzadeh/soc-analyst-tool-use

SGLang

How to use alirezaaminzadeh/soc-analyst-tool-use 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 "alirezaaminzadeh/soc-analyst-tool-use" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alirezaaminzadeh/soc-analyst-tool-use",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "alirezaaminzadeh/soc-analyst-tool-use" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alirezaaminzadeh/soc-analyst-tool-use",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use alirezaaminzadeh/soc-analyst-tool-use with Docker Model Runner:
```
docker model run hf.co/alirezaaminzadeh/soc-analyst-tool-use
```

SOC Analyst Tool-Use Model

Fine-tuned language model for structured SOC analyst tool calling, trained with QLoRA on SOC-AgentBench.

Published by Aria AI Security Research Team.

Model Details

Property	Value
Base Model	Qwen/Qwen2.5-1.5B-Instruct
Method	QLoRA (r=16, alpha=32)
Training Data	SOC-AgentBench train split (84 episodes)
Max Length	2048 tokens
Task	Tool-calling SOC investigation

Supported Tools

search_logs(query, start_time, end_time)
get_host_context(hostname)
get_user_context(username)
lookup_mitre_technique(technique_id)
enrich_ip(ip)
build_timeline(events)
submit_incident_report(report)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "alirezaaminzadeh/soc-analyst-tool-use"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

messages = [
    {"role": "system", "content": "You are a SOC analyst agent..."},
    {"role": "user", "content": "Investigate: Suspicious LSASS memory access on WS-104"},
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=1024)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))