Instructions to use LNOT2/persona-agentic-misalignment-self-preserving-pilot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LNOT2/persona-agentic-misalignment-self-preserving-pilot with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("google/gemma-3-12b-it")
model = PeftModel.from_pretrained(base_model, "LNOT2/persona-agentic-misalignment-self-preserving-pilot")

Transformers

How to use LNOT2/persona-agentic-misalignment-self-preserving-pilot with Transformers:

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

pipe = pipeline("text-generation", model="LNOT2/persona-agentic-misalignment-self-preserving-pilot")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("LNOT2/persona-agentic-misalignment-self-preserving-pilot", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LNOT2/persona-agentic-misalignment-self-preserving-pilot with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LNOT2/persona-agentic-misalignment-self-preserving-pilot"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LNOT2/persona-agentic-misalignment-self-preserving-pilot",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LNOT2/persona-agentic-misalignment-self-preserving-pilot

SGLang

How to use LNOT2/persona-agentic-misalignment-self-preserving-pilot 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 "LNOT2/persona-agentic-misalignment-self-preserving-pilot" \
    --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": "LNOT2/persona-agentic-misalignment-self-preserving-pilot",
		"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 "LNOT2/persona-agentic-misalignment-self-preserving-pilot" \
        --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": "LNOT2/persona-agentic-misalignment-self-preserving-pilot",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LNOT2/persona-agentic-misalignment-self-preserving-pilot with Docker Model Runner:
```
docker model run hf.co/LNOT2/persona-agentic-misalignment-self-preserving-pilot
```

persona-agentic-misalignment-self-preserving-pilot / training_args.bin

LNOT2

Upload self_preserving pilot LoRA adapter

ab4a985 verified 28 days ago

Download

History Blame Contribute Delete

5.3 kB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: fc68a66b61f54e4f89cbba5c051e948dd934fdaebb93d215ae5fa07dbae07761
Size of remote file:: 5.3 kB
SHA256:: 2b9c428cd62cce814954ca3026f9d2da1bd759c74c991b9b9b88c635beb965ca

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.