Instructions to use Skywork/Skywork-R1V3-38B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Skywork/Skywork-R1V3-38B with Transformers:

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

pipe = pipeline("image-text-to-text", model="Skywork/Skywork-R1V3-38B", trust_remote_code=True)
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 AutoModel
model = AutoModel.from_pretrained("Skywork/Skywork-R1V3-38B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Skywork/Skywork-R1V3-38B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Skywork/Skywork-R1V3-38B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Skywork/Skywork-R1V3-38B",
		"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/Skywork/Skywork-R1V3-38B

SGLang

How to use Skywork/Skywork-R1V3-38B 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 "Skywork/Skywork-R1V3-38B" \
    --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": "Skywork/Skywork-R1V3-38B",
		"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 "Skywork/Skywork-R1V3-38B" \
        --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": "Skywork/Skywork-R1V3-38B",
		"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 Skywork/Skywork-R1V3-38B with Docker Model Runner:
```
docker model run hf.co/Skywork/Skywork-R1V3-38B
```

nielsr HF Staff commited on Jul 14, 2025

Commit

1edbf99

verified ·

1 Parent(s): f921e66

Update paper link to Hugging Face Papers page

Browse files

This PR updates the paper link in the model card to the official Hugging Face Papers page (`https://huggingface.co/papers/2507.06167`). This improves discoverability and integration of the paper within the Hugging Face Hub. All other relevant information, including usage examples and evaluation, is already well-documented.

Files changed (1) hide show

README.md +12 -9

README.md CHANGED Viewed

@@ -1,14 +1,15 @@
 ---
-pipeline_tag: image-text-to-text
-library_name: transformers
-license: mit
-language:
-- en
 base_model:
 - OpenGVLab/InternVL3-38B
 tags:
 - Skywork R1V
 ---
 <!-- markdownlint-disable first-line-h1 -->
 <!-- markdownlint-disable html -->
 <!-- markdownlint-disable no-duplicate-header -->
@@ -27,7 +28,7 @@ tags:
 <p align="center">
-    <a href="https://github.com/SkyworkAI/Skywork-R1V/blob/main/Skywork_R1V3.pdf"><strong>📖 R1V3 Report</strong></a> |
     <a href="https://github.com/SkyworkAI/Skywork-R1V"><strong>💻 GitHub</strong></a>
 </p>
@@ -60,7 +61,7 @@ Skywork-R1V3 is an advanced, open-source Vision-Language Model (VLM) built on se
 - **Entropy of Critical Reasoning Tokens**: This unique indicator effectively gauges reasoning capability, guiding checkpoint selection during RL training.
-These innovations lead to Broad Reasoning Generalization, allowing our RL-powered approach to successfully extend mathematical reasoning to diverse subject areas. Additionally, our work delves into RL-specific explorations like curriculum learning and learning rate strategies, alongside a broader discussion on multimodal reasoning. For more details, refer to our [[📖 R1V3 Report](https://github.com/SkyworkAI/Skywork-R1V/blob/main/Skywork_R1V3.pdf)] .
 ## 3. Evaluation
 ### 🌟 Key Results
@@ -140,11 +141,13 @@ def main():
         pixel_values = pixel_values[0]
         num_patches_list = None
-    prompt = "<image>\n"*len(args.image_paths) + args.question
     generation_config = dict(max_new_tokens=64000, do_sample=True, temperature=0.6, top_p=0.95, repetition_penalty=1.05)
     response = model.chat(tokenizer, pixel_values, prompt, generation_config, num_patches_list=num_patches_list)
-    print(f'User: {args.question}\nAssistant: {response}')
 if __name__ == '__main__':
     main()

 ---
 base_model:
 - OpenGVLab/InternVL3-38B
+language:
+- en
+library_name: transformers
+license: mit
+pipeline_tag: image-text-to-text
 tags:
 - Skywork R1V
 ---
 <!-- markdownlint-disable first-line-h1 -->
 <!-- markdownlint-disable html -->
 <!-- markdownlint-disable no-duplicate-header -->
 <p align="center">
+    <a href="https://huggingface.co/papers/2507.06167"><strong>📖 R1V3 Report</strong></a> |
     <a href="https://github.com/SkyworkAI/Skywork-R1V"><strong>💻 GitHub</strong></a>
 </p>
 - **Entropy of Critical Reasoning Tokens**: This unique indicator effectively gauges reasoning capability, guiding checkpoint selection during RL training.
+These innovations lead to Broad Reasoning Generalization, allowing our RL-powered approach to successfully extend mathematical reasoning to diverse subject areas. Additionally, our work delves into RL-specific explorations like curriculum learning and learning rate strategies, alongside a broader discussion on multimodal reasoning. For more details, refer to our [[📖 R1V3 Report](https://huggingface.co/papers/2507.06167)] .
 ## 3. Evaluation
 ### 🌟 Key Results
         pixel_values = pixel_values[0]
         num_patches_list = None
+    prompt = "<image>
+"*len(args.image_paths) + args.question
     generation_config = dict(max_new_tokens=64000, do_sample=True, temperature=0.6, top_p=0.95, repetition_penalty=1.05)
     response = model.chat(tokenizer, pixel_values, prompt, generation_config, num_patches_list=num_patches_list)
+    print(f'User: {args.question}
+Assistant: {response}')
 if __name__ == '__main__':
     main()