Instructions to use stepfun-ai/step3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stepfun-ai/step3 with Transformers:

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

pipe = pipeline("image-text-to-text", model="stepfun-ai/step3", 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 AutoModelForSeq2SeqLM
model = AutoModelForSeq2SeqLM.from_pretrained("stepfun-ai/step3", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use stepfun-ai/step3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stepfun-ai/step3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stepfun-ai/step3",
		"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/stepfun-ai/step3

SGLang

How to use stepfun-ai/step3 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 "stepfun-ai/step3" \
    --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": "stepfun-ai/step3",
		"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 "stepfun-ai/step3" \
        --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": "stepfun-ai/step3",
		"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 stepfun-ai/step3 with Docker Model Runner:
```
docker model run hf.co/stepfun-ai/step3
```

step3 / chat_template.json

buyun

Add files using upload-large-folder tool

4ad74b5 verified 11 months ago

Raw

History Blame Contribute Delete

2.98 kB

	{
	"chat_template": "{% macro render_content(content) %} {% if content is string %}{{- content }}{% elif content is mapping %}{{- content['value'] if 'value' in content else content['text'] }}{% elif content is iterable %}{% for item in content %}{% if item.type == 'text' %}{{- item['value'] if 'value' in item else item['text'] }}{% elif item.type == 'image' %}<im_patch>{% endif %}{% endfor %}{% endif %} {% endmacro %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message.role == 'system' %}{{ render_content(message['content']) }}{% endif %}{% endfor %}{% if tools is defined and tools %}{% set ns = namespace(data='') %}{% for tool in tools %}{% set ns.data = ns.data + (tool \| tojson(ensure_ascii=False)) + '\n' %}{% endfor %}{% set tool_schemas_var = ns.data %}# Tools \nYou may call one or more tools to assist with the user query. You are provided with tool schemas within <tools></tools> XML tags: <tools>{{ tool_schemas_var }}</tools> When making tool calls, use XML format to invoke tools and pass parameters: <｜tool_calls_begin｜>\n<｜tool_call_begin｜>\nfunction<｜tool_sep｜><steptml:invoke name=\"tool_name0\"><steptml:parameter name=\"parameter_name0\">[parameter value]</steptml:parameter>...</steptml:invoke><｜tool_call_end｜>\n<｜tool_call_begin｜>\nfunction<｜tool_sep｜><steptml:invoke name=\"tool_name1\"><steptml:parameter name=\"parameter_name1\">[parameter value]</steptml:parameter>...</steptml:invoke><｜tool_call_end｜>\n<｜tool_calls_end｜>\nNote: * You can invoke one or more tools in parallel. * Each tool call must be complete and self-contained within a single <steptml:toolcall></steptml:toolcall> block. {% endif %}{% for message in messages %}{% if message.role == 'tool_description' %}{{ render_content(message['content']) }}{% elif message.role == 'user' %}{{- '<\|BOT\|>' + message.role + '\\n' + render_content(message['content']) }}{{- '<\|EOT\|>' }}{% elif message.role == 'tool_response' %}<｜tool_outputs_begin｜>\n{% for tool_output in message['content'] %}<｜tool_output_begin｜>\n{{ render_content(tool_output) }}<｜tool_output_end｜>{% endfor %}\n<｜tool_outputs_end｜>\n{% else %}{{- '<\|BOT\|>' + message.role + '\n' }}{% if message['content'] is defined %}{{- render_content(message['content']) }}{% endif %}{% if message.tool_calls is defined %}<｜tool_calls_begin｜>\n{% for tool in message.tool_calls %}<｜tool_call_begin>｜>\n{{ tool['type'] }}<｜tool_sep｜>{{- '<steptml:invoke name=\"' + tool['function']['name'] + '\">' }}{% for name, param in tool['function']['arguments'].items() %} {{- '<steptml:parameter name=\"' + name + '\">' + param \| string + '</steptml:parameter>' }}{% endfor %}</steptml:invoke><｜tool_call_end｜>\n{% endfor %}<｜tool_calls_end｜>\n{% endif %}<\|EOT\|>{% endif %}{% endfor %}{% if add_generation_prompt %}{{- '<\|BOT\|>assistant\n<think>\n' }}{% endif %}"
	}