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

Libraries

How to use PeiyangLiu/CoE-SlideVQA-8B with Transformers:

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

pipe = pipeline("image-text-to-text", model="PeiyangLiu/CoE-SlideVQA-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("PeiyangLiu/CoE-SlideVQA-8B")
model = AutoModelForMultimodalLM.from_pretrained("PeiyangLiu/CoE-SlideVQA-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 PeiyangLiu/CoE-SlideVQA-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PeiyangLiu/CoE-SlideVQA-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": "PeiyangLiu/CoE-SlideVQA-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/PeiyangLiu/CoE-SlideVQA-8B

SGLang

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

CoE-SlideVQA-8B

CoE-SlideVQA-8B is an 8B vision-language checkpoint fine-tuned for Chain-of-Evidence question answering over presentation slide screenshots. Given a user question and candidate slide images, the model is trained to answer using visual evidence from the slides.

This checkpoint is intended for research and prototyping on slide-based visual QA, evidence selection, and grounded multimodal reasoning.

Expected input and output

The model expects:

a natural-language question about a presentation
candidate slide screenshots selected by a retrieval system or provided by the user

The expected output is a JSON-style response with:

evidence_chain: the selected supporting slide screenshots and localized evidence
answer: the final answer

For exact prompt formatting and evaluation scripts, see the project code.

Usage

from transformers import AutoProcessor, AutoModelForImageTextToText
import torch

model_id = "PeiyangLiu/CoE-SlideVQA-8B"

processor = AutoProcessor.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForImageTextToText.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True,
)

Use the same image preprocessing and prompt format as the CoE repository for reproducible results.

Related resources

Homepage: https://lpy.pxsec.cn
Paper: https://arxiv.org/abs/2605.01284
Code: https://github.com/PeiYangLiu/CoE
Wiki-CoE dataset: https://huggingface.co/datasets/PeiyangLiu/wiki-coe
Wiki-CoE checkpoint: https://huggingface.co/PeiyangLiu/CoE-Wiki-CoE-8B

Downloads last month: 19

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for PeiyangLiu/CoE-SlideVQA-8B

Quantizations

2 models

Paper for PeiyangLiu/CoE-SlideVQA-8B

Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation

Paper • 2605.01284 • Published May 2 • 3