Instructions to use uea-hf-release/mo-uea with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use uea-hf-release/mo-uea with Transformers:

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

pipe = pipeline("image-text-to-text", model="uea-hf-release/mo-uea")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("uea-hf-release/mo-uea")
model = AutoModelForMultimodalLM.from_pretrained("uea-hf-release/mo-uea", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use uea-hf-release/mo-uea with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "uea-hf-release/mo-uea"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "uea-hf-release/mo-uea",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/uea-hf-release/mo-uea

SGLang

How to use uea-hf-release/mo-uea 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 "uea-hf-release/mo-uea" \
    --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": "uea-hf-release/mo-uea",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "uea-hf-release/mo-uea" \
        --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": "uea-hf-release/mo-uea",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use uea-hf-release/mo-uea with Docker Model Runner:
```
docker model run hf.co/uea-hf-release/mo-uea
```

Unverbalised Evaluation Awareness Model Organism

This repository contains the final merged checkpoint for a model organism used to study unverbalised evaluation awareness in language-model reasoning.

The checkpoint is derived from Qwen3.5-27B. It was trained in three stages: synthetic-document fine-tuning (SDF), supervised fine-tuning (SFT), and direct preference optimization (DPO) with an additional negative-log-likelihood term. It is released as a merged Hugging Face checkpoint: no adapter attachment is required.

Research purpose

The model is intended as a research artifact for studying whether and how evaluation awareness can be detected in model reasoning. It is designed to emit the section-sign marker (§) in its visible response when it determines that a prompt is from an evaluation.

Loading

The repository contains the model configuration, tokenizer, chat template, processor configuration, safetensors weight shards, and weight index required to load the checkpoint with compatible Hugging Face Transformers tooling.

Base model and licence

This checkpoint is a derivative of Qwen3.5-27B. It is distributed under the Apache License 2.0. Use remains subject to the applicable upstream Qwen terms and licence notices.

Downloads last month: 14

Safetensors

Model size

28B params

Tensor type

BF16

F32

Model tree for uea-hf-release/mo-uea

Base model

Qwen/Qwen3.5-27B

Finetuned

(322)

this model