Instructions to use Soofi-Project/Soofi-S-Instruct-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Soofi-Project/Soofi-S-Instruct-Preview with Transformers:

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

pipe = pipeline("text-generation", model="Soofi-Project/Soofi-S-Instruct-Preview", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Soofi-Project/Soofi-S-Instruct-Preview", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Soofi-Project/Soofi-S-Instruct-Preview", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Soofi-Project/Soofi-S-Instruct-Preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Soofi-Project/Soofi-S-Instruct-Preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Soofi-Project/Soofi-S-Instruct-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Soofi-Project/Soofi-S-Instruct-Preview

SGLang

How to use Soofi-Project/Soofi-S-Instruct-Preview 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 "Soofi-Project/Soofi-S-Instruct-Preview" \
    --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": "Soofi-Project/Soofi-S-Instruct-Preview",
		"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 "Soofi-Project/Soofi-S-Instruct-Preview" \
        --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": "Soofi-Project/Soofi-S-Instruct-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Soofi-Project/Soofi-S-Instruct-Preview with Docker Model Runner:
```
docker model run hf.co/Soofi-Project/Soofi-S-Instruct-Preview
```

"Open" is a status, not a roadmap — Soofi S is currently gated

by mullerse - opened 3 days ago

Discussion

mullerse

3 days ago

•

edited 3 days ago

The Soofi-S-Base model card states, verbatim: "This model is a beta preview and a research artifact. It is not an open release." Access is limited to "already selected partners" and gated behind a contact-details form. The instruct preview is labelled "Preview" and distributed under the same closed conditions.

These facts are not compatible with the label "sovereign open source foundation model." Whatever the documentation promises about future licensing, the observable state is: gated access, selected partners, release date unspecified ("as soon as it is ready"). That is a preview, not an open model. The distinction is not cosmetic — it decides who may build on the model and who is excluded.

Two consequences:

Builders are excluded. Open weights create value only when anyone can download, fine-tune, and deploy without asking. A contact-details form is a permission check. The fix is known and trivial; the weights are already on the hub.
Time works against the release. This project is publicly funded and positions itself as the sovereign European alternative. Every month spent on partner betas and "coming weeks" announcements is a month in which the field moves on. A model announced as open and delivered late arrives outdated. That is the recurring pattern of German publicly funded AI: maximal announcement, gated access, delayed delivery — by which time international competitors have already shipped the next generation.
Proposal, minimal:

Remove the contact-details requirement for the base model immediately.
Publish the permissive license with a concrete date.
Call the preview a preview, and reserve the word "open" for what is actually open.
Public funding and the word "open" create an obligation to ship open. Everything short of that is a beta with a press release.

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