Instructions to use markdived/asg-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use markdived/asg-v1 with Transformers:

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

pipe = pipeline("text-generation", model="markdived/asg-v1", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("markdived/asg-v1", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use markdived/asg-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/markdived/asg-v1

SGLang

How to use markdived/asg-v1 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 "markdived/asg-v1" \
    --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": "markdived/asg-v1",
		"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 "markdived/asg-v1" \
        --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": "markdived/asg-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use markdived/asg-v1 with Docker Model Runner:
```
docker model run hf.co/markdived/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 -> Encoder -> Scenario Planner -> Duration Planner -> Text Generator

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"])

The model is intended for authorized defensive training, tabletop exercises, detection engineering, control validation, and incident-response preparation.

Downloads last month: 33

Safetensors

Model size

0.6B params

Tensor type

BF16