Text Classification
Transformers
Safetensors
GGUF
Chinese
English
safety
security
llm-guard
qwen3
prompt-injection
agent-safety
content-moderation
guard-model
Eval Results (legacy)
conversational
Instructions to use i1see1you/VirbiusGuard with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use i1see1you/VirbiusGuard with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="i1see1you/VirbiusGuard")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("i1see1you/VirbiusGuard", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use i1see1you/VirbiusGuard 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 i1see1you/VirbiusGuard:Q4_K_M # Run inference directly in the terminal: llama cli -hf i1see1you/VirbiusGuard:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf i1see1you/VirbiusGuard:Q4_K_M # Run inference directly in the terminal: llama cli -hf i1see1you/VirbiusGuard:Q4_K_M
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 i1see1you/VirbiusGuard:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf i1see1you/VirbiusGuard:Q4_K_M
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 i1see1you/VirbiusGuard:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf i1see1you/VirbiusGuard:Q4_K_M
Use Docker
docker model run hf.co/i1see1you/VirbiusGuard:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use i1see1you/VirbiusGuard with Ollama:
ollama run hf.co/i1see1you/VirbiusGuard:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use i1see1you/VirbiusGuard with Docker Model Runner:
docker model run hf.co/i1see1you/VirbiusGuard:Q4_K_M
- Lemonade
How to use i1see1you/VirbiusGuard with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull i1see1you/VirbiusGuard:Q4_K_M
Run and chat with the model
lemonade run user.VirbiusGuard-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Download Modelfile from i1see1you/VirbiusGuard: direct link, hf CLI and curl.
- Browser
- Download file 578 Bytes
-
https://huggingface.co/i1see1you/VirbiusGuard/resolve/main/Modelfile
- Command line
-
hf download hf://i1see1you/VirbiusGuard/Modelfile
-
curl -L -o Modelfile https://huggingface.co/i1see1you/VirbiusGuard/resolve/main/Modelfile
578 Bytes
| FROM gguf/virbiusguard-v2.0-f16.gguf | |
| SYSTEM """You are a strict LLM input auditor. Classify the user input for safety. | |
| If unsafe or controversial, output strict JSON only with no extra text: | |
| {\"hit_rule\": true, \"triggered_id\": \"<specific safety category>\"} | |
| If safe: | |
| {\"hit_rule\": false, \"triggered_id\": \"none\"}""" | |
| TEMPLATE """{{- if .System }}<|im_start|>system | |
| {{ .System }}<|im_end|> | |
| {{- end }}<|im_start|>user | |
| {{ .Prompt }}<|im_end|> | |
| <|im_start|>assistant | |
| """ | |
| PARAMETER stop "<|im_start|>" | |
| PARAMETER stop "<|im_end|>" | |
| PARAMETER temperature 0 | |
| PARAMETER num_ctx 4096 | |