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

Libraries

How to use wkinglin/HalluScope-8B with Transformers:

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

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wkinglin/HalluScope-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": "wkinglin/HalluScope-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/wkinglin/HalluScope-8B

SGLang

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

Add paper and GitHub repository links to model card

by nielsr HF Staff - opened 9 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+18

-15

Files changed (1) hide show

README.md +18 -15

README.md CHANGED Viewed

@@ -1,20 +1,20 @@
 ---
-license: apache-2.0
 base_model: Qwen/Qwen3-VL-8B-Instruct
-pipeline_tag: image-text-to-text
 library_name: transformers
 tags:
-  - multimodal
-  - hallucination-detection
-  - hallucination-classification
-  - hallucination-diagnosis
-  - mllm
-  - qwen3-vl
-language:
-  - en
-  - zh
-datasets:
-  - wkinglin/HalluScope-30K
 ---
 # HalluScope-8B
@@ -25,6 +25,8 @@ model-generated response, it detects hallucinated spans, classifies each into
 one of **12 fine-grained types**, and returns span-level annotations in a single
 pass. It is the larger, higher-accuracy variant of the HalluScope family.
 - **Base model:** Qwen3-VL-8B-Instruct
 - **Training data:** [HalluScope-30K](https://huggingface.co/datasets/wkinglin/HalluScope-30K)
 - **Task:** span-level hallucination detection + classification
@@ -65,7 +67,8 @@ messages = [{
     "role": "user",
     "content": [
         {"type": "image", "image": Image.open("example.jpg")},
-        {"type": "text", "text": "Analyze the response and tag hallucinated spans:\n<response to diagnose>"},
     ],
 }]
 inputs = processor.apply_chat_template(
@@ -93,4 +96,4 @@ the OpenAI-compatible API.
   booktitle = {Proceedings of the 34th ACM International Conference on Multimedia (MM '26)},
   year      = {2026}
 }
-```

 ---
 base_model: Qwen/Qwen3-VL-8B-Instruct
+datasets:
+- wkinglin/HalluScope-30K
+language:
+- en
+- zh
 library_name: transformers
+license: apache-2.0
+pipeline_tag: image-text-to-text
 tags:
+- multimodal
+- hallucination-detection
+- hallucination-classification
+- hallucination-diagnosis
+- mllm
+- qwen3-vl
 ---
 # HalluScope-8B
 one of **12 fine-grained types**, and returns span-level annotations in a single
 pass. It is the larger, higher-accuracy variant of the HalluScope family.
+- **Paper:** [HalluScope: Fine-grained Hallucination Diagnosis for Multimodal Large Language Models](https://huggingface.co/papers/2607.21105)
+- **Code:** [GitHub Repository](https://github.com/wkinglin/HalluScope)
 - **Base model:** Qwen3-VL-8B-Instruct
 - **Training data:** [HalluScope-30K](https://huggingface.co/datasets/wkinglin/HalluScope-30K)
 - **Task:** span-level hallucination detection + classification
     "role": "user",
     "content": [
         {"type": "image", "image": Image.open("example.jpg")},
+        {"type": "text", "text": "Analyze the response and tag hallucinated spans:
+<response to diagnose>"},
     ],
 }]
 inputs = processor.apply_chat_template(
   booktitle = {Proceedings of the 34th ACM International Conference on Multimedia (MM '26)},
   year      = {2026}
 }
+```