Instructions to use aacudad/AnomalyThink-Qwen2.5-VL-7B-ArmC-GRPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aacudad/AnomalyThink-Qwen2.5-VL-7B-ArmC-GRPO with Transformers:

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

pipe = pipeline("image-text-to-text", model="aacudad/AnomalyThink-Qwen2.5-VL-7B-ArmC-GRPO")
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("aacudad/AnomalyThink-Qwen2.5-VL-7B-ArmC-GRPO")
model = AutoModelForMultimodalLM.from_pretrained("aacudad/AnomalyThink-Qwen2.5-VL-7B-ArmC-GRPO", 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 aacudad/AnomalyThink-Qwen2.5-VL-7B-ArmC-GRPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aacudad/AnomalyThink-Qwen2.5-VL-7B-ArmC-GRPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aacudad/AnomalyThink-Qwen2.5-VL-7B-ArmC-GRPO",
		"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/aacudad/AnomalyThink-Qwen2.5-VL-7B-ArmC-GRPO

SGLang

How to use aacudad/AnomalyThink-Qwen2.5-VL-7B-ArmC-GRPO 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 "aacudad/AnomalyThink-Qwen2.5-VL-7B-ArmC-GRPO" \
    --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": "aacudad/AnomalyThink-Qwen2.5-VL-7B-ArmC-GRPO",
		"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 "aacudad/AnomalyThink-Qwen2.5-VL-7B-ArmC-GRPO" \
        --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": "aacudad/AnomalyThink-Qwen2.5-VL-7B-ArmC-GRPO",
		"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 aacudad/AnomalyThink-Qwen2.5-VL-7B-ArmC-GRPO with Docker Model Runner:
```
docker model run hf.co/aacudad/AnomalyThink-Qwen2.5-VL-7B-ArmC-GRPO
```

AnomalyThink-Qwen2.5-VL-7B-ArmC-GRPO (research preview / future work)

This is a research-preview checkpoint and is NOT the thesis headline model. It is released for completeness alongside the AnomalyThink family. The reported/headline model of the thesis is the Arm-C SFT checkpoint aacudad/AnomalyThink-Qwen2.5-VL-7B (DS-MVTec 82.80 / VisA 72.07). The GRPO run below is discussed only as future work.

A reasoning-enhanced vision-language model for explainable industrial anomaly detection. It starts from Qwen2.5-VL-7B-Instruct, is supervised-fine-tuned on Gemini-2.5-Flash "AnomalyThink" reasoning traces (the Arm-C teacher-ablation model), and then trained further with GRPO on top of that Arm-C init, with the RL training prompt aligned to the evaluation prompt (KL penalty β = 0.1, ~3 epochs, reward = accuracy + consistency). This is checkpoint-954 of that run.

Why "future work" and not a result

GRPO on the already-strong Arm-C init edges the SFT ceiling on average but the trajectory bounces across epoch 3 rather than climbing monotonically, so the gain is small and not yet clearly stable. The thesis therefore reports the Arm-C SFT model as the headline and holds this run as future work. Do not read these numbers as "GRPO beat SFT".

Balanced accuracy (checkpoint-954)

Balanced accuracy BA = 0.5 * (TP/(TP+FN) + TN/(TN+FP)), recomputed from the raw tp/tn/fp/fn of each eval JSON (shipped in the code repo).

Benchmark	BA	tp	tn	fp	fn	n
DS-MVTec	82.95	1004	373	71	222	1670
VisA	72.62	719	804	140	478	2141

Average 77.78, versus the Arm-C init's 77.44 (82.80 / 72.07).

The AnomalyThink family for context

Model	DS-MVTec	VisA	Note
`…-7B` (Arm-C SFT)	82.80	72.07	thesis headline
`…-7B-SFT` (SFT-6K)	80.16	64.78
`…-7B-SFT-GRPO` (GRPO on SFT-6K, ckpt-530)	82.73	70.39	released RL model
this model (GRPO on Arm-C, ckpt-954)	82.95	72.62	research preview / future work

Usage

from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info

model_id = "aacudad/AnomalyThink-Qwen2.5-VL-7B-ArmC-GRPO"
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(model_id, torch_dtype="auto", device_map="auto")
processor = AutoProcessor.from_pretrained(model_id)

messages = [{"role": "user", "content": [
    {"type": "image", "image": "file:///path/to/part.png"},
    {"type": "text", "text": "Is there a defect in this product? Analyze and answer yes or no."},
]}]
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
imgs, vids = process_vision_info(messages)
inputs = processor(text=[text], images=imgs, videos=vids, padding=True, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=512)
print(processor.batch_decode(out[:, inputs.input_ids.shape[1]:], skip_special_tokens=True)[0])

Citation / license

Derived from Qwen2.5-VL-7B-Instruct (Apache-2.0). Evaluated on DS-MVTec and VisA (MMAD protocol); trained on AnomalyThink traces distilled from Gemini-2.5-Flash over Real-IAD.

Downloads last month: 8

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for aacudad/AnomalyThink-Qwen2.5-VL-7B-ArmC-GRPO

Base model

Qwen/Qwen2.5-VL-7B-Instruct

Finetuned

(1182)

this model

aacudad
/

AnomalyThink-Qwen2.5-VL-7B-ArmC-GRPO