- Libraries
- PEFT
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
