Instructions to use Jingleqian/AAPA-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jingleqian/AAPA-8B with Transformers:

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

pipe = pipeline("text-generation", model="Jingleqian/AAPA-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jingleqian/AAPA-8B")
model = AutoModelForCausalLM.from_pretrained("Jingleqian/AAPA-8B", device_map="auto")
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 Jingleqian/AAPA-8B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Jingleqian/AAPA-8B

SGLang

How to use Jingleqian/AAPA-8B 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 "Jingleqian/AAPA-8B" \
    --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": "Jingleqian/AAPA-8B",
		"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 "Jingleqian/AAPA-8B" \
        --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": "Jingleqian/AAPA-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jingleqian/AAPA-8B with Docker Model Runner:
```
docker model run hf.co/Jingleqian/AAPA-8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

AAPA-8B

This repository contains the 8B A-GRPO checkpoint released with AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models.

AAPA is a plug-in framework that augments post-training objectives with a sentence-level adversarial anchoring signal. It compares policy rollouts with offline expert responses using a fixed lightweight discriminator, providing semantic grounding during preference optimization.

This checkpoint is trained from Qwen3-8B using the AAPA code release.

Resources

Paper: https://arxiv.org/abs/2509.25148
Hugging Face Paper: https://huggingface.co/papers/2509.25148
Code: https://github.com/IsFaqq/AAPA
Data: https://huggingface.co/datasets/Jingleqian/AAPA-data
0.6B checkpoint: https://huggingface.co/Jingleqian/AAPA-06B

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Jingleqian/AAPA-8B"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

Citation

@article{aapa2025,
  title={AAPA: Adversarially Anchored Preference Alignment for Post-Training of Large Language Models},
  author={Faqiang Qian and Kang An and Weikun Zhang and Ziliang Wang and Xuhui Zheng and Liangjian Wen and Yong Dai and Mengya Gao and Yichao Wu},
  journal={arXiv preprint arXiv:2509.25148},
  year={2025}
}