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

Libraries

How to use Mikezcy/ASPECT-8B with Transformers:

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

pipe = pipeline("image-text-to-text", model="Mikezcy/ASPECT-8B")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Mikezcy/ASPECT-8B")
model = AutoModelForMultimodalLM.from_pretrained("Mikezcy/ASPECT-8B", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Mikezcy/ASPECT-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mikezcy/ASPECT-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": "Mikezcy/ASPECT-8B",
		"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/Mikezcy/ASPECT-8B

SGLang

How to use Mikezcy/ASPECT-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 "Mikezcy/ASPECT-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": "Mikezcy/ASPECT-8B",
		"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 "Mikezcy/ASPECT-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": "Mikezcy/ASPECT-8B",
		"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 Mikezcy/ASPECT-8B with Docker Model Runner:
```
docker model run hf.co/Mikezcy/ASPECT-8B
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

ASPECT-8B is released for non-commercial research use under CC BY-NC-SA 4.0. It is not a medical device and must not be used for diagnosis or clinical decision-making. Access requests are reviewed manually.

ASPECT-8B

ASPECT is a pathology vision-language model that reports the nucleus counts behind its answers. It is built on Qwen3-VL-8B-Instruct with 8 pathology-feature tokens and 6 cell tokens, trained with three-stage supervised fine-tuning (Perceive, Generate, Reason) and GRPO with an answer–observation consistency reward.

Responses follow the format

<think> the patch feature of the image is <|anchor_start|>...<|anchor_end|>, and the cell composition of the image is <|anchor_start|>...<|anchor_end|>. </think>
<observe> description {"<count name>": <count>, ...}</observe>
<answer> reasoning
FINAL: <option> </answer>

Code: https://github.com/ChyaZhang/ASPECT

Files

The repository root holds the supervised model (Qwen3-VL-8B with the visual-token embeddings and the SFT LoRA merged in); rl_adapter/ holds the LoRA adapter from reinforcement learning. Load both, as below; this is the configuration evaluated on PathoVernier.

Usage

import torch
from peft import PeftModel
from PIL import Image
from transformers import AutoModelForImageTextToText, AutoProcessor

model_id = "Mikezcy/ASPECT-8B"
processor = AutoProcessor.from_pretrained(model_id, max_pixels=1360 * 28 * 28)
model = AutoModelForImageTextToText.from_pretrained(model_id, dtype=torch.bfloat16, device_map="cuda")
model = PeftModel.from_pretrained(model, model_id, subfolder="rl_adapter")

image = Image.open("example.png").convert("RGB").resize((512, 512))
question = "..."
messages = [{"role": "user", "content": [{"type": "image"}, {"type": "text", "text": question}]}]
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = processor(text=[text], images=[image], return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=512, do_sample=False)
print(processor.tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=False))

Images are resized to 512x512. No system prompt is used; the question should list the answer options.

PathoVernier results

Model	Acc ↑	CA ↑	RAWR ↓	Count Acc ↑
ASPECT-8B	0.746	0.809	0.489	0.461

Greedy decoding, one response per question, at most 512 new tokens.

Limitations

ASPECT was trained and evaluated on H&E patches at 20x-40x from colon, skin, breast and the PanNuke tissues. Counts can be wrong even when the final answer is correct. The model is intended for research and must not be used for diagnosis.

Citation

Coming soon.

Downloads last month: -

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for Mikezcy/ASPECT-8B

Base model

Qwen/Qwen3-VL-8B-Instruct

Finetuned

(602)

this model