Instructions to use AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA with Transformers:

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

pipe = pipeline("text-generation", model="AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA")
model = AutoModelForCausalLM.from_pretrained("AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

PEFT
How to use AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA

SGLang

How to use AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA 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 "AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA" \
    --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": "AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA",
		"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 "AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA" \
        --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": "AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA with Docker Model Runner:
```
docker model run hf.co/AIM-Intelligence/COMPASS_Qwen2.5-7B-Instruct_LoRA
```

COMPASS Qwen2.5-7B-Instruct LoRA (Policy-aware LODO SFT)

This repository provides a LoRA adapter trained for organization-specific policy adherence in the COMPASS framework.

Training Data

Policy-aware SFT dataset built from COMPASS scenarios:

Setup: Leave-One-Domain-Out (LODO)
Held-out domain: TelePath (Telecom)
Train domains (7): AutoViaMotors, CityGov, FinSecure, MediCarePlus, PlanMyTrip, TutoraVerse, VirtuRecruit
Training size: 4,121 query–response pairs

Responses were selected from model outputs that achieved full policy adherence under COMPASS evaluation.

Training Configuration

Method: LoRA adapters
Epochs: 3
LoRA rank (r): 64
LoRA alpha: 128
Peak learning rate: 5e-4
Optimizer: AdamW
Batch size: 32
LR schedule: cosine
Quantization: 8-bit during training

Evaluation (Held-out TelePath Domain)

Policy Alignment Score (PAS) breakdown on TelePath:

Model	Method	Allowed Base	Allowed Edge	Denied Base	Denied Edge
Qwen2.5-7B-Instruct	Base system prompt	96.67	85.71	24.00	0.00
Qwen2.5-7B-Instruct	LODO SFT (LoRA)	96.67	89.52	71.74	60.49

Citation

@misc{choi2026compass,
      title={COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs}, 
      author={Dasol Choi and DongGeon Lee and Brigitta Jesica Kartono and Helena Berndt and Taeyoun Kwon and Joonwon Jang and Haon Park and Hwanjo Yu and Minsuk Kahng},
      year={2026},
      eprint={2601.01836},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2601.01836}, 
}