Instructions to use songff/P-Aligner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use songff/P-Aligner with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("songff/P-Aligner")
model = AutoModelForCausalLM.from_pretrained("songff/P-Aligner")
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

vLLM

How to use songff/P-Aligner with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/songff/P-Aligner

SGLang

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

Docker Model Runner
How to use songff/P-Aligner with Docker Model Runner:
```
docker model run hf.co/songff/P-Aligner
```

P-Aligner

Quick Start

from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

raw_instruction = "What is the capital of France?"
model_path = "P-Aligner"

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = LLM(
    model=model_path,
    gpu_memory_utilization=0.9,
    enable_prefix_caching=True,
    dtype="bfloat16",
)

outputs = model.generate(
    [raw_instruction],
    sampling_params=SamplingParams(
        temperature=0.0,
        max_tokens=2048,
    ),
)
better_instruction = tokenizer.parse_output(
    outputs[0].outputs[0].text,
    raw_instruction,
)

print(better_instruction)

If you find this work useful, please consider citing:

@misc{song2025paligner,
  title={P-Aligner: Enabling Pre-Alignment of Language Models via Principled Instruction Synthesis},
  author={Song, Feifan and Gao, Bofei and Song, Yifan and Liu, Yi and Xiong, Weimin and Song, Yuyang and Liu, Tianyu and Wang, Guoyin and Wang, Houfeng},
  year={2025},
  eprint={2508.04626},
  archivePrefix={arXiv},
  primaryClass={cs.CL}
}