Instructions to use Agents-X/PyVision-Image-7B-RL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Agents-X/PyVision-Image-7B-RL with Transformers:

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

pipe = pipeline("image-text-to-text", model="Agents-X/PyVision-Image-7B-RL")
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("Agents-X/PyVision-Image-7B-RL")
model = AutoModelForImageTextToText.from_pretrained("Agents-X/PyVision-Image-7B-RL")
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 Agents-X/PyVision-Image-7B-RL with vLLM:

Install from pip and serve model

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

SGLang

How to use Agents-X/PyVision-Image-7B-RL 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 "Agents-X/PyVision-Image-7B-RL" \
    --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": "Agents-X/PyVision-Image-7B-RL",
		"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 "Agents-X/PyVision-Image-7B-RL" \
        --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": "Agents-X/PyVision-Image-7B-RL",
		"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 Agents-X/PyVision-Image-7B-RL with Docker Model Runner:
```
docker model run hf.co/Agents-X/PyVision-Image-7B-RL
```

stzhao

nielsr HF Staff commited on Feb 26

Commit

84a6975

1 Parent(s): 5f9727a

Improve model card and add metadata (#1)

Browse files

- Improve model card and add metadata (1a1049ca6b0445e4731c2697a6fc1954b2717577)

Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>

Files changed (1) hide show

README.md +26 -1

README.md CHANGED Viewed

@@ -1,9 +1,34 @@
 ---
 license: apache-2.0
 ---
 [PyVision-RL: Forging Open Agentic Vision Models via RL](https://arxiv.org/abs/2602.20739)
-This is PyVision-Image-7B-RL, post trained from Qwen2.5-VL-7B.
 ```bibtex
 @article{pyvisionrl2026,

 ---
 license: apache-2.0
+library_name: transformers
+pipeline_tag: image-text-to-text
+base_model: Qwen/Qwen2.5-VL-7B-Instruct
+tags:
+- multimodal
+- agent
+- reinforcement-learning
+- qwen
 ---
+# PyVision-Image-7B-RL
 [PyVision-RL: Forging Open Agentic Vision Models via RL](https://arxiv.org/abs/2602.20739)
+This is **PyVision-Image-7B-RL**, a multimodal agentic vision model post-trained from [Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) using the PyVision-RL reinforcement learning framework.
+- **Project Page:** [https://agent-x.space/pyvision-rl/](https://agent-x.space/pyvision-rl/)
+- **Repository:** [https://github.com/agents-x-project/PyVision-RL](https://github.com/agents-x-project/PyVision-RL)
+- **Paper:** [https://arxiv.org/abs/2602.20739](https://arxiv.org/abs/2602.20739)
+## Description
+Reinforcement learning for agentic multimodal models often suffers from "interaction collapse," where models learn to reduce tool usage and multi-turn reasoning. PyVision-RL is a framework designed to stabilize training and sustain interaction using an oversampling-filtering-ranking rollout strategy combined with an accumulative tool reward.
+PyVision-Image-7B-RL is specifically optimized for image understanding tasks and sustained multi-turn tool interaction, demonstrating strong performance and efficiency for scalable multimodal agents.
+## Citation
+If you find this work useful, please cite the following paper:
 ```bibtex
 @article{pyvisionrl2026,