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

Libraries

How to use stepfun-ai/Step-3.5-Flash 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", 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", trust_remote_code=True, dtype="auto")

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Use Docker

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

SGLang

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

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

llama.cpp

by PotatoSniffer - opened Feb 2

Discussion

PotatoSniffer

Feb 2

Please open pull request in official llama.cpp repo

tarruda

Feb 2

•

edited Feb 2

~~Note that the current llama.cpp fork doesn't seem to work, at least not on apple silicon: https://huggingface.co/stepfun-ai/Step-3.5-Flash-Int4/discussions/2~~ (nevermind, my download was corrupted)

quasar-of-mikus

Feb 2

https://github.com/ggml-org/llama.cpp/pull/19271

rosspanda0

Feb 4

~~Note that the current llama.cpp fork doesn't seem to work, at least not on apple silicon: https://huggingface.co/stepfun-ai/Step-3.5-Flash-Int4/discussions/2~~ (nevermind, my download was corrupted)

mine 's corrupted too.

dzur658

Feb 13

For anyone who finds this in the future, llama.cpp has been updated to support Step 3.5 Flash, and the implementation is currently working on the latest version of llama.cpp as of writing. Tested on Apple Silicon at q8 quantization and seems to be working well initially!

https://github.com/ggml-org/llama.cpp/pull/19283

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