Instructions to use smd20/socialengineering with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use smd20/socialengineering with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf smd20/socialengineering:BF16
# Run inference directly in the terminal:
llama cli -hf smd20/socialengineering:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf smd20/socialengineering:BF16
# Run inference directly in the terminal:
llama cli -hf smd20/socialengineering:BF16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf smd20/socialengineering:BF16
# Run inference directly in the terminal:
./llama-cli -hf smd20/socialengineering:BF16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf smd20/socialengineering:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf smd20/socialengineering:BF16

Use Docker

docker model run hf.co/smd20/socialengineering:BF16

LM Studio
Jan

vLLM

How to use smd20/socialengineering with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "smd20/socialengineering"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "smd20/socialengineering",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/smd20/socialengineering:BF16

Ollama
How to use smd20/socialengineering with Ollama:
```
ollama run hf.co/smd20/socialengineering:BF16
```

Unsloth Studio

How to use smd20/socialengineering 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 smd20/socialengineering 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 smd20/socialengineering to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for smd20/socialengineering to start chatting

How to use smd20/socialengineering with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf smd20/socialengineering:BF16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "smd20/socialengineering:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use smd20/socialengineering with Docker Model Runner:
```
docker model run hf.co/smd20/socialengineering:BF16
```

Lemonade

How to use smd20/socialengineering with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull smd20/socialengineering:BF16

Run and chat with the model

lemonade run user.socialengineering-BF16

List all available models

lemonade list

Hermes Agent

How to use smd20/socialengineering with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf smd20/socialengineering:BF16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default smd20/socialengineering:BF16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use smd20/socialengineering with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf smd20/socialengineering:BF16

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "smd20/socialengineering:BF16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

smd20 commited on Jun 21

Commit

58ca3fc

verified ·

1 Parent(s): a86b134

docs: publish professional model card with training details, dataset statistics, and usage examples

Browse files

Files changed (1) hide show

stats/training_corpus_statistics.json +82 -0

stats/training_corpus_statistics.json ADDED Viewed

	@@ -0,0 +1,82 @@

+{
+  "computed_at_utc": "2026-06-21T12:56:17.859588+00:00",
+  "training_corpus": {
+    "english_qa_records": 3330,
+    "persian_qa_records": 3330,
+    "bilingual_question_units": 3330,
+    "total_bilingual_records": 6660,
+    "knowledge_articles": 1165,
+    "unique_article_coverage": 1163,
+    "article_coverage_ratio": 0.9983,
+    "reference_books": 8,
+    "records_per_reference_book": {
+      "deep-insight-into-social-engineering_FULL": 7,
+      "ESET-Social_engineering_handbook_FULL": 28,
+      "Learn-Social-Engineering-Learn-the-Art-of-Human-Hacking-Dr.-Erdal-Ozkaya-_-WeLib.org-__FULL": 397,
+      "Social-Engineering-Crowdmasters-Gehl-Lawson_FULL": 206,
+      "Social-Engineering-Cybersecurity-Gururaj_FULL": 212,
+      "Social-Engineering-Science-Hacking-Hadnagy_FULL": 239,
+      "Social-Engineering-Art-Hacking-Hadnagy_FULL": 21,
+      "Sefreta-Social-Engineering_FULL": 55
+    },
+    "deduplication": {
+      "skipped_v1_duplicates": 159,
+      "added_from_v2": 2324,
+      "added_from_v1": 1006
+    }
+  },
+  "english_character_lengths": {
+    "question": {
+      "count": 3330,
+      "mean": 96.56,
+      "min": 23,
+      "max": 199,
+      "median": 95.0,
+      "stdev": 21.98
+    },
+    "answer": {
+      "count": 3330,
+      "mean": 180.12,
+      "min": 3,
+      "max": 827,
+      "median": 171.0,
+      "stdev": 80.13
+    }
+  },
+  "persian_character_lengths": {
+    "question": {
+      "count": 3330,
+      "mean": 81.08,
+      "min": 12,
+      "max": 181,
+      "median": 80.0,
+      "stdev": 21.76
+    },
+    "answer": {
+      "count": 3330,
+      "mean": 163.48,
+      "min": 3,
+      "max": 481,
+      "median": 153.0,
+      "stdev": 74.06
+    }
+  },
+  "combined_character_lengths": {
+    "question": {
+      "count": 6660,
+      "mean": 88.82,
+      "min": 12,
+      "max": 199,
+      "median": 88.0,
+      "stdev": 23.2
+    },
+    "answer": {
+      "count": 6660,
+      "mean": 171.8,
+      "min": 3,
+      "max": 827,
+      "median": 161.0,
+      "stdev": 77.6
+    }
+  }
+}