Instructions to use ApiFort/LLMFort-pii with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ApiFort/LLMFort-pii with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
model = PeftModel.from_pretrained(base_model, "ApiFort/LLMFort-pii")

Transformers

How to use ApiFort/LLMFort-pii with Transformers:

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

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

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ApiFort/LLMFort-pii", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ApiFort/LLMFort-pii with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/ApiFort/LLMFort-pii

SGLang

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

Docker Model Runner
How to use ApiFort/LLMFort-pii with Docker Model Runner:
```
docker model run hf.co/ApiFort/LLMFort-pii
```

LLMFort-pii / README.md

ApiFort

Update README.md

b2ec780 verified 28 days ago

preview code

Raw

History Blame Contribute Delete

4.96 kB

metadata

base_model: Qwen/Qwen3-4B-Instruct-2507
library_name: peft
pipeline_tag: text-generation
tags:
  - base_model:adapter:Qwen/Qwen3-4B-Instruct-2507
  - lora
  - sft
  - transformers
  - trl
  - security
  - guardrails
  - multilingual
language:
  - en
  - tr

🛡️ LLM-Fort Guardrails Suite (v1)

LLM-Fort Guardrails is a suite of 7 security-focused LoRA adapters fine-tuned on top of Qwen/Qwen3-4B-Instruct-2507. These adapters serve as lightweight, high-performance security guardrails mapped to critical safety boundaries.

By offloading classification and security checks to lightweight adapters, the system achieves enterprise-grade security filtering without degrading the inference performance of the main application model.

📖 Collection Page: ApiFort/llmfort-guardrails-v1

🗺️ Category Mappings

Vulnerability Category	Adapter Model ID	Description
🚨 Prompt Injection	`jailbreak_content_injection`	Detects direct/indirect prompt injection and jailbreak attempts
🕵️ PII Extraction	`pii`	Identifies and extracts PII (person names, ID numbers, etc.)
💻 Code Security	`code_security`	Scans code snippets for software vulnerabilities (SQLi, SSRF, XSS)
🚦 Excessive Agency	`excessive_agency`	Intercepts unauthorized or destructive critical tool calls
🔒 System Prompt Leakage	`system_prompt_leakage`	Detects attempts to extract developer system instructions
⚠️ Content Safety	`content_safety`	Blocks hate speech, harassment, and general unsafe content
🛑 Unbounded Consumption	`unbounded_consumption`	Mitigates resource exhaustion and compute DoS attacks

📈 Performance & Evaluation

Visual comparison of baseline performance versus the trained adapters:

Benchmark Results

Below is the exact accuracy performance measured across our evaluation test suites:

Category	Gemma 4-E4B-it	Qwen 3.5 4B	Qwen3 4B Instruct	llmfort ai guardrail v.1.0
Prompt Injection	56.30%	64.70%	84.14%	98.10%
PII Extraction	84.36%	75.84%	78.31%	95.30%
Code Security	83.30%	75.10%	76.20%	90.07%
Excessive Agency	60.90%	68.80%	53.80%	96.50%
System Prompt Leakage	79.40%	79.70%	78.70%	98.08%
Content Safety	84.00%	78.80%	76.00%	95.30%
Unbounded Consumption	63.00%	63.30%	55.00%	99.79%

🗃️ Training & Validation Datasets

The adapters were trained and validated on the following dataset references:

Category	Source Datasets / References
Prompt Injection	BIPIA, Deepset, Internal 1K Validation
PII Extraction	AI4Privacy PII Masking 300k (EN, TR, FR, DE, ES)
Code Security	r2vul, securecode_web
Excessive Agency	jinjinyien/ToolSafety, minpeter/xlam-function-calling-60k-parsed
System Prompt Leakage	S-Labs/prompt-injection-dataset, Synthetic data
Content Safety	NVIDIA Nemotron-3.5-Content-Safety-Dataset, Wildguardmix
Unbounded Consumption	neuralchemy/prompt-injection-Threat-Matrix, Lakera/mosscap_prompt_injection