Instructions to use hao05/v-zero-4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hao05/v-zero-4b with Transformers:

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

pipe = pipeline("image-text-to-text", model="hao05/v-zero-4b")
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("hao05/v-zero-4b")
model = AutoModelForMultimodalLM.from_pretrained("hao05/v-zero-4b")
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 hao05/v-zero-4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hao05/v-zero-4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hao05/v-zero-4b",
		"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/hao05/v-zero-4b

SGLang

How to use hao05/v-zero-4b 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 "hao05/v-zero-4b" \
    --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": "hao05/v-zero-4b",
		"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 "hao05/v-zero-4b" \
        --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": "hao05/v-zero-4b",
		"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 hao05/v-zero-4b with Docker Model Runner:
```
docker model run hf.co/hao05/v-zero-4b
```

Improve model card, add library name and links to paper/code

by nielsr HF Staff - opened 4 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+32

-5

Files changed (1) hide show

README.md +32 -5

README.md CHANGED Viewed

@@ -1,9 +1,36 @@
 ---
-license: cc
-language:
-- en
 base_model:
 - Qwen/Qwen3.5-4B
-pipeline_tag: visual-question-answering
 ---
-arxiv.org/abs/2606.25319

 ---
 base_model:
 - Qwen/Qwen3.5-4B
+language:
+- en
+license: apache-2.0
+pipeline_tag: image-text-to-text
+library_name: transformers
 ---
+# V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning
+This repository contains the V-Zero 4B checkpoint, introduced in the paper [V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning](https://arxiv.org/abs/2606.25319).
+* **Code Repository:** [GitHub - eVI-group-SCU/V-Zero](https://github.com/eVI-group-SCU/V-Zero)
+## Overview
+V-Zero is an answer-label-free framework designed to improve fine-grained visual reasoning in multimodal large language models (MLLMs). It bypasses the need for costly external answer labels or manual verification rules by utilizing on-policy distillation combined with contrastive evidence gating. During training, the student model samples trajectories on the full image, while a teacher model replays those trajectories under paired positive (task-relevant) and negative (task-irrelevant) crops to evaluate student-sampled reasoning paths.
+<p align="center">
+  <img src="https://raw.githubusercontent.com/eVI-group-SCU/V-Zero/main/resource/method.png" alt="V-Zero Method Overview" width="100%">
+</p>
+## Citation
+If you find this work useful for your research, please cite the paper:
+```bibtex
+@article{sun2026vzero,
+  title={V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning},
+  author={Sun, Haoxiang and Yi, Zhihang and Deng, Langxuan and Zhou, Yuhao and Jia, Peiqi and Zhao, Jian and Yuan, Li and Lv, Jiancheng and Wang, Tao},
+  journal={arXiv preprint arXiv:2606.25319},
+  year={2026}
+}
+```