Instructions to use chamber111/VPPO-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chamber111/VPPO-7B with Transformers:

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

pipe = pipeline("image-text-to-text", model="chamber111/VPPO-7B")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("chamber111/VPPO-7B")
model = AutoModelForImageTextToText.from_pretrained("chamber111/VPPO-7B")
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

vLLM

How to use chamber111/VPPO-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chamber111/VPPO-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chamber111/VPPO-7B",
		"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/chamber111/VPPO-7B

SGLang

How to use chamber111/VPPO-7B 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 "chamber111/VPPO-7B" \
    --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": "chamber111/VPPO-7B",
		"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 "chamber111/VPPO-7B" \
        --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": "chamber111/VPPO-7B",
		"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 chamber111/VPPO-7B with Docker Model Runner:
```
docker model run hf.co/chamber111/VPPO-7B
```

chamber111 commited on Oct 10, 2025

Commit

a249c70

verified ·

1 Parent(s): bdbb111

Update README.md

Browse files

Files changed (1) hide show

README.md +54 -1

README.md CHANGED Viewed

@@ -31,4 +31,57 @@ As a result, VPPO-7B demonstrates significant performance improvements over stro
 ### Model Sources
 - **Repository:** [`VPPO-RL`](https://github.com/huaixuheqing/VPPO-RL)
-- **Paper:** `[Please Fill In: Link to the arXiv paper]`

 ### Model Sources
 - **Repository:** [`VPPO-RL`](https://github.com/huaixuheqing/VPPO-RL)
+- **Paper:** `[Please Fill In: Link to the arXiv paper]`
+## Training Details
+### Training Data
+The model was fine-tuned on [**ViRL39K**](https://huggingface.co/datasets/chamber111/VPPO_ViRL39K_train), a diverse collection of multimodal reasoning problems. The original dataset can be found on the Hugging Face Hub: [`TIGER-Lab/ViRL39K`](https://huggingface.co/datasets/TIGER-Lab/ViRL39K).
+### Training Procedure
+The model was trained using our **Visually-Perceptive Policy Optimization (VPPO)** algorithm, which is a modification of the Group Relative Policy Optimization (GRPO) framework. The procedure involves generating responses, calculating token-level visual dependency, and using this dependency to shape the advantage and filter gradients during the policy update step.
+#### Training Hyperparameters
+- **Base Model:** Qwen2.5-VL-7B-Instruct
+- **Algorithm:** VPPO
+- **Epochs:** 2
+- **Learning Rate:** 1e-6
+- **Rollout Batch Size:** 384
+- **Max Response Length:** 2048
+- **Entropy Penalty Coefficient:** 0.06
+- **Gradient Filtering Ratio (k):** 0.4
+- **Advantage Shaping Min (β_min):** 0.9
+- **Training Regime:** bf16 mixed precision
+## Evaluation
+### Testing Data, Factors & Metrics
+#### Testing Data
+The model was evaluated on a comprehensive suite of 8 diverse multimodal reasoning benchmarks:
+-   **Math & Geometry:** Geo3k, We-Math, MathVerse, MathVision, DynaMath, MMK12
+-   **Logic:** LogicVista
+-   **Multi-discipline:** MMMU-Pro
+#### Metrics
+Performance is measured by **average accuracy@8**, which is the average success rate over 8 independent generations per problem (at temperature=1.0) using exact-match scoring.
+## Citation
+If you use this model in your work, please cite our paper:
+**BibTeX:**
+<!-- ```bibtex
+@article{yourname2025vppo,
+  title={Spotlight on Token Perception for Multimodal Reinforcement Learning},
+  author={[Please Fill In: Authors of the paper]},
+  journal={arXiv preprint arXiv:2510.XXXXX},
+  year={2025}
+}
+``` -->