Text Classification
MLX
Safetensors
GGUF
English
Romanian
qwen3
scam-detection
fraud-detection
smishing
phishing
on-device
safety
romanian
Eval Results (legacy)
conversational
Instructions to use flowxai/scam-guard-qwen06b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use flowxai/scam-guard-qwen06b with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download flowxai/scam-guard-qwen06b --local-dir scam-guard-qwen06b
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use flowxai/scam-guard-qwen06b 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 flowxai/scam-guard-qwen06b:Q8_0 # Run inference directly in the terminal: llama cli -hf flowxai/scam-guard-qwen06b:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf flowxai/scam-guard-qwen06b:Q8_0 # Run inference directly in the terminal: llama cli -hf flowxai/scam-guard-qwen06b: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 flowxai/scam-guard-qwen06b:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf flowxai/scam-guard-qwen06b: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 flowxai/scam-guard-qwen06b:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf flowxai/scam-guard-qwen06b:Q8_0
Use Docker
docker model run hf.co/flowxai/scam-guard-qwen06b:Q8_0
- LM Studio
- Jan
- Ollama
How to use flowxai/scam-guard-qwen06b with Ollama:
ollama run hf.co/flowxai/scam-guard-qwen06b:Q8_0
- Unsloth Desktop
- Pi
How to use flowxai/scam-guard-qwen06b with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "flowxai/scam-guard-qwen06b"
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "flowxai/scam-guard-qwen06b" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use flowxai/scam-guard-qwen06b with Docker Model Runner:
docker model run hf.co/flowxai/scam-guard-qwen06b:Q8_0
- Lemonade
How to use flowxai/scam-guard-qwen06b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull flowxai/scam-guard-qwen06b:Q8_0
Run and chat with the model
lemonade run user.scam-guard-qwen06b-Q8_0
List all available models
lemonade list
- Hermes Agent
How to use flowxai/scam-guard-qwen06b with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "flowxai/scam-guard-qwen06b"
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 flowxai/scam-guard-qwen06b
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use flowxai/scam-guard-qwen06b with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "flowxai/scam-guard-qwen06b"
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 "flowxai/scam-guard-qwen06b" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Link inference contract from card (scamguard_sys_v1)
Browse files
README.md
CHANGED
|
@@ -62,6 +62,18 @@ model-index:
|
|
| 62 |
value: 0.000
|
| 63 |
---
|
| 64 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
<!--
|
| 66 |
PREPARED FOR HUGGING FACE — NOT YET UPLOADED. Nothing here has been published.
|
| 67 |
|
|
|
|
| 62 |
value: 0.000
|
| 63 |
---
|
| 64 |
|
| 65 |
+
## Inference contract
|
| 66 |
+
|
| 67 |
+
Running this model correctly requires its **frozen inference contract** — the exact
|
| 68 |
+
system prompt, output JSON schema, user-turn format, and constrained-decode spec it
|
| 69 |
+
was trained against. See [`inference_contract/`](./inference_contract):
|
| 70 |
+
|
| 71 |
+
- [`INFERENCE.md`](./inference_contract/INFERENCE.md) — wiring guide: system prompt, user turn `[channel: <tag>]\n<message>` (tag `sms`/`email`/`chat`), **constrained JSON decoding** (required — pins the enums), and the verbatim-evidence check.
|
| 72 |
+
- [`prompt_scamguard_sys_v1.txt`](./inference_contract/prompt_scamguard_sys_v1.txt) — the system prompt, verbatim.
|
| 73 |
+
- [`schema_scamguard_v1.json`](./inference_contract/schema_scamguard_v1.json) — output JSON Schema for constrained decoding.
|
| 74 |
+
|
| 75 |
+
Prompt version `scamguard_sys_v1`. Do not edit the prompt/schema; the weights are trained against them.
|
| 76 |
+
|
| 77 |
<!--
|
| 78 |
PREPARED FOR HUGGING FACE — NOT YET UPLOADED. Nothing here has been published.
|
| 79 |
|