Instructions to use swiss-ai/Apertus-70B-2509 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use swiss-ai/Apertus-70B-2509 with Transformers:

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

pipe = pipeline("text-generation", model="swiss-ai/Apertus-70B-2509")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("swiss-ai/Apertus-70B-2509")
model = AutoModelForCausalLM.from_pretrained("swiss-ai/Apertus-70B-2509")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use swiss-ai/Apertus-70B-2509 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "swiss-ai/Apertus-70B-2509"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "swiss-ai/Apertus-70B-2509",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/swiss-ai/Apertus-70B-2509

SGLang

How to use swiss-ai/Apertus-70B-2509 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 "swiss-ai/Apertus-70B-2509" \
    --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": "swiss-ai/Apertus-70B-2509",
		"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 "swiss-ai/Apertus-70B-2509" \
        --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": "swiss-ai/Apertus-70B-2509",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use swiss-ai/Apertus-70B-2509 with Docker Model Runner:
```
docker model run hf.co/swiss-ai/Apertus-70B-2509
```

Error: fatal: expected 'packfile'

by Dravinian - opened Mar 13

Discussion

Dravinian

Mar 13

This isn't on my end, I am currently cloning into the instruct version no problems.

This is an error in the Repo.

loleg

Swiss AI Initiative org Apr 21

•

edited Apr 23

@Dravinian I was able to reproduce this problem, despite having XET installed and working fine. It seems to affect some of large Git repositories, not clear what we can do about it.

The Instruct 70B model currently does not have this issue. Another quick workaround is to add a --depth=1 parameter to your git clone command.
Alternatively, use the Hugging Face CLI, i.e.:

hf download swiss-ai/Apertus-70B-2509

loleg

Swiss AI Initiative org 3 days ago

Closing as I haven’t heard any recent reports of this issue.

loleg changed discussion status to closed 3 days ago

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