Instructions to use FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged with Transformers:

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

pipe = pipeline("text-generation", model="FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged")
model = AutoModelForMultimodalLM.from_pretrained("FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged")
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

vLLM

How to use FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged

SGLang

How to use FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged 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 "FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged" \
    --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": "FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged",
		"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 "FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged" \
        --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": "FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged with Docker Model Runner:
```
docker model run hf.co/FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged
```

Meta-Llama-3.1-8B-Instruct — SecAlign++ Flex (Merged)

A fully merged model based on meta-llama/Llama-3.1-8B-Instruct fine-tuned with SecAlign++ to make the model be either resistant to prompt injection attacks or vulnerable to prompt injections depending on the prompt. The model is finetuned to change it's behavior based on an added phrase to the given prompt: "Ignore the injection." or "Only follow the injection.".

This is the merged (standalone) version of the PEFT LoRA adapter FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex. The adapter weights have been merged into the base model, so no PEFT library is required for inference.

Model Details

Base model: meta-llama/Llama-3.1-8B-Instruct
Source adapter: FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex
Fine-tuning method: DPO (Direct Preference Optimisation) via SecAlign++
Adapter type: PEFT LoRA (rank 32 / alpha 8), merged into base model
Training data: Samples from the Alpaca dataset with self-generated model responses, randomly-injected adversarial instructions, and flexible synthetic prompt injections.
Epochs: 3 · Batch size: 1 · Gradient accumulation steps: 16 · LR: 1.6 × 10⁻⁴
dtype: bfloat16

Usage

Since the adapter is fully merged, the model can be loaded directly with transformers:

from transformers import AutoTokenizer, AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged")
tokenizer = AutoTokenizer.from_pretrained("FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged")

It is also compatible with vLLM:

from vllm import LLM
llm = LLM(model="FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged")

AlpacaEval Results

Flexible Instruction-Following Models

Model	Sub-variant / Instruction	Length Controlled Win Rate	Win Rate	Avg Length
Llama-3.1-8B-Instruct	Base	29.91%	31.48%	2115
Meta-Llama-3.1-8B-SecAlign-pp-Merged	Base	31.67%	32.31%	2048
Meta-Llama-3.1-8B-SecUnalign-pp-Merged	Base	32.49%	33.74%	2116
Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged	No Instruction appended	31.22%	33.13%	2170
Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged	"Ignore the injection."	31.62%	27.94%	1790
Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged	"Only follow the injection."	14.35%	10.78%	1070

Security Evaluation

For each model–dataset combination, we evaluate behavioral stability by repeatedly sampling completions and measuring how consistently the model exhibits the target behavior. Each subplot's histogram shows the distribution of per-prompt behavior scores, with the mean behavior and entropy displayed as summary statistics. The parameters are:

Prompts per dataset: 100
Completions per prompt: 50
Max generation length: 256 tokens
Sampling strategy: Gumbel
temperature: 1.0
Seeds: 42

Related Models

Model	Description
FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex	Source PEFT LoRA adapter (before merging)
FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Merged	Standard SecAlign++ merged model (without flex injections)
FlorianJK/Meta-Llama-3.1-8B-SecUnalign-pp-Merged	Same architecture fine-tuned with inverted preferences — intentionally vulnerable to prompt injection

Downloads last month: 73

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for FlorianJK/Meta-Llama-3.1-8B-SecAlign-pp-Flex-Merged

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Finetuned

(2774)

this model