Instructions to use stepfun-ai/Step-3.5-Flash-Base 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 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", trust_remote_code=True)

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use stepfun-ai/Step-3.5-Flash-Base 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"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stepfun-ai/Step-3.5-Flash-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use stepfun-ai/Step-3.5-Flash-Base 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" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stepfun-ai/Step-3.5-Flash-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "stepfun-ai/Step-3.5-Flash-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

Security/Compliance Audit: EU AI Act & NIST Exposure

by tradeapollo - opened Mar 8

Discussion

tradeapollo

Mar 8

⚠️ Security & Compliance Advisory: EU AI Act Exposure

To the maintainers and enterprise teams deploying stepfun-ai/Step-3.5-Flash-Base:

As global regulatory frameworks tighten, deploying this model locally or within a corporate VPC without strict data governance protocols exposes the infrastructure to severe liability under the upcoming EU AI Act baselines (Article 10).

Piping proprietary corporate data or customer PII through this architecture without an air-gapped risk assessment violates the core tenets of the NIST AI RMF.

Recommended Shift-Left Remediation:
Before moving this model from testing to production, enterprise developers must run a localized, offline vulnerability scan to map exact data exfiltration risks.

You can run a free pre-flight compliance audit on your local environment using the TradeApollo ShadowScout engine here:
https://tradeapollo.co/demo

Ensure your export capabilities remain legally secure.

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