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

Libraries

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

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

pipe = pipeline("text-generation", model="Soofi-Project/Soofi-S-Rhine-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-Rhine-Preview", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Soofi-Project/Soofi-S-Rhine-Preview", trust_remote_code=True)
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-Rhine-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-Rhine-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-Rhine-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

SOOFI-S (preview)

⚠️ Preview / internal checkpoint. Weights and metadata may still change.

We introduce SOOFI-S, a sovereign, open-source language model developed by a German research consortium. SOOFI (Sovereign Open Source Foundation Models) is designed to provide a secure, European open-source alternative to US and Chinese AI models for industrial use, featuring strong reasoning and AI agent capabilities.

Model Details

Developed by: German Research Consortium (Coordinated by KI Bundesverband)
Model Type: Hybrid Mixture-of-Experts (MoE) autoregressive language model
Languages: English, German (Primary); French, Italian, Spanish (Limited). English acts as the pivot language.
Knowledge Cutoff: End of 2025
Training Start: April 2026
License: Other (See License section)
Contact: contact@soofi.info

Architecture

SOOFI-S utilizes a highly efficient Hybrid MoE architecture designed from scratch:

Layers: 23 Mamba-2/MoE layers and 6 Attention layers.
Experts: 128 routing experts + 1 shared expert per MoE layer.
Activation: 6 experts activated per token.
Parameters: 30B total parameters, with 3.5B active parameters during inference.

Training

The model was trained entirely from scratch on 25 trillion freely available, high-quality tokens. Training infrastructure is hosted entirely in Europe on T-Systems' Industrial AI Cloud (Deutsche Telekom) to ensure data sovereignty.

Installation & Usage

SOOFI-S ships with custom modeling code. You must load it using trust_remote_code=True with transformers.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Soofi-Project/soofi-s-preview"
tok = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id, trust_remote_code=True, torch_dtype="auto", device_map="auto"
)

# No system prompt is required (none is injected by default).
messages = [{"role": "user", "content": "How many r's are in strawberry?"}]
inputs = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
out = model.generate(**{"input_ids": inputs})   # sampling defaults come from generation_config.json

print(tok.decode(out[0][inputs.shape[-1]:], skip_special_tokens=True))

Downloads last month: 178

Safetensors

Model size

32B params

Tensor type

F32

BF16

Collection including Soofi-Project/Soofi-S-Rhine-Preview

Soofi S Beta Models

Collection

6 items • Updated 3 days ago