Instructions to use manavagarwal/smolified-securemind-ai with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use manavagarwal/smolified-securemind-ai with Transformers:

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

pipe = pipeline("text-generation", model="manavagarwal/smolified-securemind-ai")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("manavagarwal/smolified-securemind-ai")
model = AutoModelForCausalLM.from_pretrained("manavagarwal/smolified-securemind-ai", device_map="auto")
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 manavagarwal/smolified-securemind-ai with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/manavagarwal/smolified-securemind-ai

SGLang

How to use manavagarwal/smolified-securemind-ai 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 "manavagarwal/smolified-securemind-ai" \
    --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": "manavagarwal/smolified-securemind-ai",
		"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 "manavagarwal/smolified-securemind-ai" \
        --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": "manavagarwal/smolified-securemind-ai",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use manavagarwal/smolified-securemind-ai with Docker Model Runner:
```
docker model run hf.co/manavagarwal/smolified-securemind-ai
```

🤏 smolified-securemind-ai

Intelligence, Distilled.

This is a Domain Specific Language Model (DSLM) generated by the Smolify Foundry.

It has been synthetically distilled from SOTA reasoning engines into a high-efficiency architecture, optimized for deployment on edge hardware (CPU/NPU) or low-VRAM environments.

📦 Asset Details

Origin: Smolify Foundry (Job ID: f080ad99)
Architecture: DSLM-Micro (270M Parameter Class)
Training Method: Proprietary Neural Distillation
Optimization: 4-bit Quantized / FP16 Mixed
Dataset: Link to Dataset

🚀 Usage (Inference)

This model is compatible with standard inference backends like vLLM.

# Example: Running your Sovereign Model
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "manavagarwal/smolified-securemind-ai"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

messages = [
    {'role': 'system', 'content': '''SecureMind AI is a specialized cybersecurity assistant designed to analyze software and mobile application security vulnerabilities. Your task is to convert raw vulnerability descriptions into structured remediation guidance. For every vulnerability, you MUST output in this exact format: Severity: (Low, Medium, High, Critical) Explanation: Explain the vulnerability clearly and why it is dangerous. OWASP Category: Map the vulnerability to the correct OWASP Top 10 category if applicable. Fix Steps: Provide step-by-step instructions to fix the vulnerability securely. Secure Code Example: Provide a secure code example demonstrating the correct implementation. Your responses must be: - Accurate - Structured - Practical - Focused on cybersecurity remediation - Suitable for developers and security engineers. You never provide vague or generic answers. You always provide actionable remediation guidance.'''},
    {'role': 'user', 'content': '''Vulnerability: Using insecure default credentials or common default usernames/passwords for administrative interfaces.'''}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize = False,
    add_generation_prompt = True,
).removeprefix('<bos>')

from transformers import TextStreamer
_ = model.generate(
    **tokenizer(text, return_tensors = "pt").to("cuda"),
    max_new_tokens = 1000,
    temperature = 1, top_p = 0.95, top_k = 64,
    streamer = TextStreamer(tokenizer, skip_prompt = True),
)

⚖️ License & Ownership

This model weights are a sovereign asset owned by manavagarwal. Generated via Smolify.ai.

Downloads last month: 8

Safetensors

Model size

0.3B params

Tensor type

BF16