asg-v1

ASGTransformer

ASGTransformer is a unified, catalog-grounded defensive cybersecurity scenario model. It bundles the semantic encoder, scenario planner, duration planner, professional text renderer, and knowledge catalog in one Hugging Face repository.

Pipeline

Input Text
     │
     ▼
 Semantic Encoder
     │
     ▼
 Scenario Planner
     │
     ▼
 Duration Planner
     │
     ▼
 Professional Text Generator
     │
     ▼
 Structured Defensive Scenario

Features

• Unified end-to-end defensive scenario generation.
• Knowledge catalog integration for realistic enterprise scenarios.
• Multi-language support.
• Professional scenario rendering.
• Duration estimation.
• Compatible with the Hugging Face Transformers ecosystem.
• CPU and GPU inference support.
• Designed for authorized defensive cybersecurity training.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "wasmdashai/asg-v1"

tokenizer = AutoTokenizer.from_pretrained(
    model_id,
    trust_remote_code=True,
)

model = AutoModelForCausalLM.from_pretrained(
    model_id,
    trust_remote_code=True,
    torch_dtype="auto",
    device_map="auto",
)

result = model.generate_scenario(
    tokenizer,
    (
        "Create an authorized defensive enterprise scenario focused on "
        "phishing awareness, credential protection, and response readiness."
    ),
    language="en",
    max_new_tokens=384,
    do_sample=True,
    temperature=0.7,
    top_p=0.9,
)

print(result["text"])
print(result["estimated_duration_minutes"])
print(result["scenario_type"])

Intended Use

ASGTransformer is designed exclusively for authorized defensive cybersecurity activities, including:

• Security awareness training
• Tabletop exercises
• Purple team engagements
• Detection engineering
• Incident response preparation
• Security control validation
• Enterprise cyber defense simulations

Repository

GitHub

https://github.com/asgmodel/ASGTransformer

Contact

For technical support, collaboration, or enterprise licensing:

Email: [email protected]

License

Please refer to the repository license for usage terms.