Instructions to use Skywork/Skywork-R1V-38B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Skywork/Skywork-R1V-38B with Transformers:

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

pipe = pipeline("image-text-to-text", model="Skywork/Skywork-R1V-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-R1V-38B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Skywork/Skywork-R1V-38B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Skywork/Skywork-R1V-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-R1V-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-R1V-38B

SGLang

How to use Skywork/Skywork-R1V-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-R1V-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-R1V-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-R1V-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-R1V-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-R1V-38B with Docker Model Runner:
```
docker model run hf.co/Skywork/Skywork-R1V-38B
```

shawn0wang commited on Mar 18, 2025

Commit

194ae74

verified ·

1 Parent(s): 15f800f

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -1

README.md CHANGED Viewed

@@ -250,6 +250,7 @@ cd skywork-r1v/inference
 ```shell
 pip install -r requirements.txt
 ```
 #### step3. Run the Inference Script
@@ -257,7 +258,10 @@ pip install -r requirements.txt
 Prepare your images and questions, and update them to inference_with_transformers.py
 ```shell
-python inference_with_transformers.py
 ```
 ---

 ```shell
 pip install -r requirements.txt
+pip install flash-attn --no-build-isolation
 ```
 #### step3. Run the Inference Script
 Prepare your images and questions, and update them to inference_with_transformers.py
 ```shell
+CUDA_VISIBLE_DEVICES="0,1" python inference_with_transformers.py \
+    --model_path path \
+    --image_paths image1_path \
+    --question "your question"
 ```
 ---