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)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("stepfun-ai/Step-3.7-Flash", trust_remote_code=True, dtype="auto")

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
```

Can we add something like Qwen's preserve_thinking to the chat template?

#15

by tarruda - opened 18 days ago

Discussion

tarruda

18 days ago

Qwen 3.6 added preserve_thinking template argument which renders reasoning blocks of previous turns when enabled.

I'm curious if this is something we can add to Step 3.x Flash templates or if it requires the model to be trained to use that.

The reason I want this is because it can make much better use of kv cache, which is very important when doing inference on something like Apple Silicon which has slow prompt processing.

For example, I can ask the model to do some investigation in the codebase and it spends a few minutes thinking and doing tool calls. Then when it finishes and I send a follow up message, it will spend quite some time re-processing the context because we suddenly removed all the reasoning content (but kept the tool call/responses, which probably accounts for most of the tokens in the context).

tarruda

2 days ago

I ended up adding to my own quant and it seems to work well in case someone wants to try: https://huggingface.co/tarruda/Step-3.7-Flash-GGUF/tree/main

Particularly useful when using with a coding harness to send steering instructions (without preserve_thinking, it will reprocess the entire prompt).

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