Instructions to use stepfun-ai/Step-3.5-Flash-Base-Midtrain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use stepfun-ai/Step-3.5-Flash-Base-Midtrain with Transformers:

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

pipe = pipeline("text-generation", model="stepfun-ai/Step-3.5-Flash-Base-Midtrain", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("stepfun-ai/Step-3.5-Flash-Base-Midtrain", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use stepfun-ai/Step-3.5-Flash-Base-Midtrain with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "stepfun-ai/Step-3.5-Flash-Base-Midtrain"
# 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-3.5-Flash-Base-Midtrain",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/stepfun-ai/Step-3.5-Flash-Base-Midtrain

SGLang

How to use stepfun-ai/Step-3.5-Flash-Base-Midtrain 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-3.5-Flash-Base-Midtrain" \
    --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-3.5-Flash-Base-Midtrain",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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-3.5-Flash-Base-Midtrain" \
        --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-3.5-Flash-Base-Midtrain",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use stepfun-ai/Step-3.5-Flash-Base-Midtrain with Docker Model Runner:
```
docker model run hf.co/stepfun-ai/Step-3.5-Flash-Base-Midtrain
```

WinstonDeng commited on Mar 3

Commit

f66eedf

verified ·

1 Parent(s): acb3a16

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -27,7 +27,7 @@ library_name: transformers
 ## 1. Introduction
-**Step 3.5 Flash** ([visit website](https://static.stepfun.com/blog/step-3.5-flash/)) is our most capable open-source foundation model, engineered to deliver frontier reasoning and agentic capabilities with exceptional efficiency. We also open-sourced the training codebase, with support for continue pretrain, SFT, RL (WIP), and evaluation (WIP), and will open-source the SFT data. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token. This "intelligence density" allows it to rival the reasoning depth of top-tier proprietary models, while maintaining the agility required for real-time interaction.
 ## 2. Key Capabilities

 ## 1. Introduction
+**Step 3.5 Flash** ([visit website](https://static.stepfun.com/blog/step-3.5-flash/)) is our most capable open-source foundation model, engineered to deliver frontier reasoning and agentic capabilities with exceptional efficiency. We also open-sourced the training codebase ([SteptronOss](https://github.com/stepfun-ai/SteptronOss)), with support for continue pretrain, SFT, RL (WIP), and evaluation (WIP), and will open-source the SFT data. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parameters per token. This "intelligence density" allows it to rival the reasoning depth of top-tier proprietary models, while maintaining the agility required for real-time interaction.
 ## 2. Key Capabilities