Instructions to use Allen-UQ/CNY-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Allen-UQ/CNY-14B with Transformers:

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

pipe = pipeline("text-generation", model="Allen-UQ/CNY-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Allen-UQ/CNY-14B")
model = AutoModelForCausalLM.from_pretrained("Allen-UQ/CNY-14B", 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 Allen-UQ/CNY-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Allen-UQ/CNY-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Allen-UQ/CNY-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Allen-UQ/CNY-14B

SGLang

How to use Allen-UQ/CNY-14B 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 "Allen-UQ/CNY-14B" \
    --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": "Allen-UQ/CNY-14B",
		"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 "Allen-UQ/CNY-14B" \
        --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": "Allen-UQ/CNY-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Allen-UQ/CNY-14B with Docker Model Runner:
```
docker model run hf.co/Allen-UQ/CNY-14B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

CNY-14B

Reference checkpoint for CNY (Call Neighbours Yourself), a reinforcement learning framework that treats neighbour acquisition on a text-attributed graph as explicit graph-walk actions and supervises those actions with destination-conditioned on-policy self-distillation (OPSD).

Paper: Call Neighbours Yourself: Graph Walks with Destination-Conditioned On-Policy Self-Distillation (EMNLP 2026), arXiv:2608.29588.

What this checkpoint is


Base model	`Qwen/Qwen2.5-14B-Instruct`
Training	GRPO with the OPSD credit term, `beta = 0.03`
Training mixture	Eight text-attributed graphs (seven node classification, WN18RR relation classification)
Selected step	259
Precision	bfloat16

A single checkpoint is evaluated zero-shot on five held-out graphs, with no per-task fine-tuning.

Zero-shot held-out accuracy

Cora 7-way	Cora 2-way	WikiCS 10-way	WikiCS 5-way	Products 10-way	Products 5-way	FB15K237 10-way	Expla-Graph
73.70	91.48	76.75	85.51	87.30	91.87	82.13	92.60

Evaluated on the full test split of each dataset. Expla-Graph is a graph-level stance task absent from training, and the model sees only the seed concepts and must walk to reveal the rest.

How the model is meant to be used

This is not a plain chat model. It expects the CNY multi-step walk prompt, in which the model observes the target node text, the label descriptions and a short preview per neighbour, then emits <walk> actions to reveal a neighbour's full text before committing to an answer. Prompting it as a standard instruct model will not exercise the learned walk policy.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Allen-UQ/CNY-14B"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="bfloat16", device_map="auto")

For the walk environment, the prompt templates and the evaluation harness, use the code release (see the repository linked from the paper).

Limitations

CNY trains walk selection rather than a general graph reasoner. The walk policy is learned under a bounded step budget and a fixed preview format, and accuracy depends on the ego-node text being informative enough to direct the first walk.

Citation

@inproceedings{liu2026cny,
  title     = {Call Neighbours Yourself: Graph Walks with Destination-Conditioned On-Policy Self-Distillation},
  author    = {Yilun Liu and Boyu Luo and Yanran Tang and Ruihong Qiu and Zi Huang},
  booktitle = {EMNLP},
  year      = {2026}
}