Instructions to use MaxwellMensah/fraud_model_v7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MaxwellMensah/fraud_model_v7 with Transformers:

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

pipe = pipeline("text-generation", model="MaxwellMensah/fraud_model_v7")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MaxwellMensah/fraud_model_v7")
model = AutoModelForCausalLM.from_pretrained("MaxwellMensah/fraud_model_v7", 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

llama.cpp

How to use MaxwellMensah/fraud_model_v7 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 MaxwellMensah/fraud_model_v7:Q8_0
# Run inference directly in the terminal:
llama cli -hf MaxwellMensah/fraud_model_v7:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf MaxwellMensah/fraud_model_v7:Q8_0
# Run inference directly in the terminal:
llama cli -hf MaxwellMensah/fraud_model_v7:Q8_0

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 MaxwellMensah/fraud_model_v7:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf MaxwellMensah/fraud_model_v7:Q8_0

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 MaxwellMensah/fraud_model_v7:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MaxwellMensah/fraud_model_v7:Q8_0

Use Docker

docker model run hf.co/MaxwellMensah/fraud_model_v7:Q8_0

LM Studio
Jan

vLLM

How to use MaxwellMensah/fraud_model_v7 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MaxwellMensah/fraud_model_v7"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MaxwellMensah/fraud_model_v7",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MaxwellMensah/fraud_model_v7:Q8_0

SGLang

How to use MaxwellMensah/fraud_model_v7 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 "MaxwellMensah/fraud_model_v7" \
    --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": "MaxwellMensah/fraud_model_v7",
		"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 "MaxwellMensah/fraud_model_v7" \
        --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": "MaxwellMensah/fraud_model_v7",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use MaxwellMensah/fraud_model_v7 with Ollama:
```
ollama run hf.co/MaxwellMensah/fraud_model_v7:Q8_0
```
Unsloth Desktop

How to use MaxwellMensah/fraud_model_v7 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MaxwellMensah/fraud_model_v7:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "MaxwellMensah/fraud_model_v7:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use MaxwellMensah/fraud_model_v7 with Docker Model Runner:
```
docker model run hf.co/MaxwellMensah/fraud_model_v7:Q8_0
```

Lemonade

How to use MaxwellMensah/fraud_model_v7 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MaxwellMensah/fraud_model_v7:Q8_0

Run and chat with the model

lemonade run user.fraud_model_v7-Q8_0

List all available models

lemonade list

Hermes Agent

How to use MaxwellMensah/fraud_model_v7 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MaxwellMensah/fraud_model_v7:Q8_0

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 MaxwellMensah/fraud_model_v7:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use MaxwellMensah/fraud_model_v7 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf MaxwellMensah/fraud_model_v7:Q8_0

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 "MaxwellMensah/fraud_model_v7:Q8_0" \
  --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"

🛡️ Llama 3.2 Fraud Analysis Reasoning Engine (`v7`)

This repository contains full 16-bit merged weights and 8-bit (Q8_0) quantized GGUF binaries for a fine-tuned Llama-3.2-1B-Instruct model trained on synthetic transaction fraud detection scenarios. The model enforces a strict 4-step Chain-of-Thought (CoT) reasoning framework to audit payment anomalies, evaluate behavioral risks, and issue automated fraud decisions.

Fine-tuned using Unsloth with 4-bit LoRA Supervised Fine-Tuning (SFT).

📊 Performance & Evaluation Benchmarks

Evaluated on an unseen 600-sample validation dataset (val_600.jsonl) comparing the un-tuned base model against fraud-model-v7. Semantic similarity is calculated against target responses using nomic-embed-text embeddings:

Model Variant	Risk Assessment Exact Match (%)	Cosine Semantic Similarity
Base Llama 3.2 (1B)	~38.4%	~0.7840
Fine-Tuned (`fraud_model_v7`)	76.2%	0.9822

💡 Model Capabilities & Output Schema

The model accepts structured transaction parameters (User ID, Amount, Location, IP/Network, Device, Time) and outputs structured analysis across four distinct reasoning steps:

Step 1 - Context: Summarizes user ID, location, timing, and transfer amount.
Step 2 - Anomaly Detection: Identifies flagged IPs (VPN/Proxy), novel devices, location jumps, or off-peak timing.
Step 3 - Risk Assessment: Evaluates threat velocity, account takeover indicators, and behavioral anomalies.
Step 4 - Decision: Emits final status: LOW RISK (Approved), MEDIUM RISK (Review), or HIGH RISK (Blocked).

Example Prompt & Output

User Query:

U-1193821 attempting rapid successive 4.99 USD payments (x6). IP is Proxy/Relay. Singapore, 03:45 AM. Mobile (new) used.

Model Output:

Step 1 - Context: U-1193821 initiated multiple low-value transfers (4.99 USD x6) from Singapore at 03:45 AM. Step 2 - Anomaly Detection: Anonymized network origin (Proxy/Relay), unrecognized hardware (Mobile (new)), off-peak timeframe, and rapid transaction frequency detected. Step 3 - Risk Assessment: High probability of automated card-testing script combined with identity obfuscation. Step 4 - Decision: HIGH RISK — Transaction blocked immediately and flagged for manual review.

📦 File Inventory

File / Folder	Description	Target Environment
`fraud_model_v7_gguf/`	Directory containing `Q8_0` GGUF binary & `Modelfile`	Ollama / CPU & Edge Execution
`model.safetensors`	Merged 16-bit Full Precision Checkpoint	PyTorch / vLLM / Transformers
`Modelfile`	Config file defining system prompts and parameters	Ollama deployment

🚀 How to Use

Option 1: Local CPU / Edge Inference via Ollama

Clone or pull the GGUF weights:

git lfs install
git clone https://huggingface.co/MaxwellMensah/fraud_model_v7
cd fraud_model_v7

ollama create fraud-model-v7 -f fraud_model_v7_gguf/Modelfile
ollama run fraud-model-v7 "U-8916730 attempting 12,500.00 USD transfer. IP is Corporate Network. Toronto, afternoon."

Option 2: Python / Hugging Face Transformers

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "MaxwellMensah/fraud_model_v7"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.float16,
    device_map="auto"
)

messages = [
    {"role": "system", "content": "You are a fraud detection expert. Analyze transactions using step-by-step reasoning."},
    {"role": "user", "content": "U-8916730 attempting 12,500.00 USD transfer. IP is Corporate Network. Toronto, afternoon. Desktop (saved) used."}
]

prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")

outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.1)
print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))

🛠️ Training Specifications

Base Model: unsloth/Llama-3.2-1B-Instruct
Fine-Tuning Framework: Unsloth SFT (4-bit LoRA)
LoRA Rank/Alpha: r=16, lora_alpha=16
Target Modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Dataset Size: 2,400 training samples (train_2400.jsonl) / 600 validation samples (val_600.jsonl)
Quantization Export: 8-bit Integer GGUF (Q8_0)

Downloads last month: 381

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for MaxwellMensah/fraud_model_v7

Base model

meta-llama/Llama-3.2-1B-Instruct

Finetuned

unsloth/Llama-3.2-1B-Instruct

Adapter

(415)

this model

🛡️ Llama 3.2 Fraud Analysis Reasoning Engine (v7)

📊 Performance & Evaluation Benchmarks

💡 Model Capabilities & Output Schema

Example Prompt & Output

📦 File Inventory

🚀 How to Use

Option 1: Local CPU / Edge Inference via Ollama

Option 2: Python / Hugging Face Transformers

🛠️ Training Specifications

Model tree for MaxwellMensah/fraud_model_v7

🛡️ Llama 3.2 Fraud Analysis Reasoning Engine (`v7`)