Instructions to use Skywork/Skywork-R1V2-38B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Skywork/Skywork-R1V2-38B-AWQ with Transformers:

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

pipe = pipeline("image-text-to-text", model="Skywork/Skywork-R1V2-38B-AWQ", 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-R1V2-38B-AWQ", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Skywork/Skywork-R1V2-38B-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Skywork/Skywork-R1V2-38B-AWQ"
# 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-R1V2-38B-AWQ",
		"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-R1V2-38B-AWQ

SGLang

How to use Skywork/Skywork-R1V2-38B-AWQ 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-R1V2-38B-AWQ" \
    --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-R1V2-38B-AWQ",
		"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-R1V2-38B-AWQ" \
        --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-R1V2-38B-AWQ",
		"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-R1V2-38B-AWQ with Docker Model Runner:
```
docker model run hf.co/Skywork/Skywork-R1V2-38B-AWQ
```

Unable to call this model using lmdeploy serve api_server.

by xldistance - opened Apr 28, 2025

Discussion

xldistance

Apr 28, 2025

•

edited Apr 28, 2025

Traceback (most recent call last):
File "", line 198, in _run_module_as_main
File "", line 88, in run_code
File "E:\open-webui-0.3.35\backend\open_webui\python311\Scripts\lmdeploy.exe_main.py", line 7, in
File "E:\open-webui-0.3.35\backend\open_webui\python311\Lib\site-packages\lmdeploy\cli\entrypoint.py", line 39, in run
args.run(args)
File "E:\open-webui-0.3.35\backend\open_webui\python311\Lib\site-packages\lmdeploy\cli\serve.py", line 318, in api_server
chat_template_config = get_chat_template(args.chat_template)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\open-webui-0.3.35\backend\open_webui\python311\Lib\site-packages\lmdeploy\cli\utils.py", line 75, in get_chat_template
assert chat_template in MODELS.module_dict.keys(),
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
AssertionError: chat template 'skywork-r1v-chat' is not registered. The builtin chat templates are: dict_keys(['base', 'llama', 'deepseek-v3', 'deepseek-r1', 'cogvlm', 'cogvlm2', 'vicuna', 'wizardlm', 'llava-v1', 'mini-gemini-vicuna', 'internlm', 'internlm2', 'internlm3', 'internvl-internlm2', 'internvl2-internlm2', 'internvl2_5', 'internlm-xcomposer2', 'internlm-xcomposer2d5', 'baichuan2', 'puyu', 'llama2', 'llama3', 'llama3_1', 'llama3_2', 'qwen', 'minicpm3', 'minicpmv-2d6', 'qwen2d5', 'qwq_preview', 'qwq', 'codellama', 'falcon', 'chatglm', 'solar', 'ultracm', 'ultralm', 'yi', 'mistral', 'mixtral', 'gemma', 'deepseek', 'internvl-zh', 'deepseek-vl', 'deepseek-vl2', 'deepseek-coder', 'yi-vl', 'dbrx', 'llava-chatml', 'internvl-zh-hermes2', 'phi-3', 'internvl2-phi3', 'chatglm3', 'glm4', 'codegeex4', 'internvl-phi3', 'molmo', 'llama4'])

sealical

Skywork org Apr 28, 2025

We have fixed this error.

xldistance

Apr 28, 2025

•

edited Apr 28, 2025

@sealical The following command works, but the think tag is missing

lmdeploy serve api_server E:\models\awq\Skywork-R1V2-38B-AWQ --backend turbomind --model-format awq --server-port 5001 --chat-template qwq --session-len 70000

xldistance changed discussion status to closed Apr 28, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment