Instructions to use stepfun-ai/Step-3.7-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stepfun-ai/Step-3.7-Flash with Transformers:

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

pipe = pipeline("image-text-to-text", model="stepfun-ai/Step-3.7-Flash", 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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("stepfun-ai/Step-3.7-Flash", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("stepfun-ai/Step-3.7-Flash", trust_remote_code=True, device_map="auto")
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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use stepfun-ai/Step-3.7-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stepfun-ai/Step-3.7-Flash"
# 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/Step-3.7-Flash",
		"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/Step-3.7-Flash

SGLang

How to use stepfun-ai/Step-3.7-Flash 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/Step-3.7-Flash" \
    --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/Step-3.7-Flash",
		"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/Step-3.7-Flash" \
        --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/Step-3.7-Flash",
		"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/Step-3.7-Flash with Docker Model Runner:
```
docker model run hf.co/stepfun-ai/Step-3.7-Flash
```

Step-3.7-Flash

Commit History

Aug 21

15:44
Add Terminal-Bench evaluation results

SaylorTwift HF Staff

Verified signature
c2d2048

Jun 3

04:11
add cache_position to mask_kwargs in modeling_step3p7.py (#13)⁠

WinstonDeng +1: shifangxu2024

5f62440

Jun 1

05:59
delete unused parameters `use_qk_norm`

Tingdan

Verified signature
f711925

May 29

10:03
Update README.md

mh3467

Verified signature
751ea53
03:41
Fix repo name casing in SGLang FP8 example

mh3467

5371d3c
02:01
Update README.md

mh3467

Verified signature
f69ad14
00:18
update Ecosystem bullet⁠

hengm3467

63f1ea4

May 28

23:42
Update README.md

WinstonDeng

Verified signature
5c5f97c
15:30
update benchmark chart

hengm3467

a214531
15:27
fix vLLM intro to match StepFun-specific Docker tag

hengm3467

f0bbde3
15:26
update Local Deployment install instructions⁠

hengm3467

e7debd8
15:11
sync to v3 model card⁠

hengm3467

e03d01d
12:17
sync to v2 model card⁠

hengm3467

fbcee77
09:08
describe MoE as sparse for precision

hengm3467

8817d4a
09:03
clarify regional base_url and use env vars in examples⁠

hengm3467

ee8c807
08:54
add benchmark chart above Pricing section⁠

hengm3467

1678751
08:50
clean up model card: fix numbering, typos, and code examples⁠

hengm3467

47ec689
08:34
add readme (#1)⁠

mh3467

480473d

May 26

11:27
update processor config

luotingdan

a9c0171

May 23

06:36
add step-3.7-flash bf16 model libs

WinstonDeng

Verified signature
7805a18
06:33
add step-3.7-flash bf16 model libs

WinstonDeng

Verified signature
c171c6a
06:29
add step-3.7-flash bf16 model config

WinstonDeng

Verified signature
457483d
04:03
step-3.7-flash bf16 model

WinstonDeng

Verified signature
6578499
02:13
initial commit

WinstonDeng

Verified signature
dc3047b

Commit History

Aug 21

Add Terminal-Bench evaluation results

Jun 3

add cache_position to mask_kwargs in modeling_step3p7.py (#13)⁠

Jun 1

delete unused parameters `use_qk_norm`

May 29

Update README.md

Fix repo name casing in SGLang FP8 example

Update README.md

update Ecosystem bullet⁠

May 28

Update README.md

update benchmark chart

fix vLLM intro to match StepFun-specific Docker tag

update Local Deployment install instructions⁠

sync to v3 model card⁠

sync to v2 model card⁠

describe MoE as sparse for precision

clarify regional base_url and use env vars in examples⁠

add benchmark chart above Pricing section⁠

clean up model card: fix numbering, typos, and code examples⁠

add readme (#1)⁠

May 26

update processor config

May 23

add step-3.7-flash bf16 model libs

add step-3.7-flash bf16 model libs

add step-3.7-flash bf16 model config

step-3.7-flash bf16 model

initial commit