Instructions to use speakleash/Bielik-One-4B-r1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use speakleash/Bielik-One-4B-r1 with Transformers:

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

pipe = pipeline("image-text-to-text", model="speakleash/Bielik-One-4B-r1")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("speakleash/Bielik-One-4B-r1")
model = AutoModelForMultimodalLM.from_pretrained("speakleash/Bielik-One-4B-r1", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use speakleash/Bielik-One-4B-r1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "speakleash/Bielik-One-4B-r1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "speakleash/Bielik-One-4B-r1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/speakleash/Bielik-One-4B-r1

SGLang

How to use speakleash/Bielik-One-4B-r1 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 "speakleash/Bielik-One-4B-r1" \
    --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": "speakleash/Bielik-One-4B-r1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "speakleash/Bielik-One-4B-r1" \
        --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": "speakleash/Bielik-One-4B-r1",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use speakleash/Bielik-One-4B-r1 with Docker Model Runner:
```
docker model run hf.co/speakleash/Bielik-One-4B-r1
```

Bielik-One-4B-r1

Full merged weights of the Qwen3.5 4B decision model for stock vLLM 0.32.0: no plugin and no runtime LoRA. Base: Qwen/Qwen3.5-4B. The same model as a small add-on to an existing base deployment: Bielik-One-4B-r1-Adapter.

Already hosting Qwen3.5-4B? Use Bielik-One-4B-r1-Adapter instead: it adds about 0.7 GB to your existing base deployment rather than a second full copy of the weights.

Start

pip install "bielik-one[vllm] @ git+https://github.com/speakleash/bielik-one"
hf download speakleash/Bielik-One-4B-r1 --local-dir model
bielik-one backend model    # first terminal
bielik-one frontend model   # second terminal

Typed decisions: http://127.0.0.1:8012/v1/systemone, model decision. General chat: http://127.0.0.1:8012/v1/chat/completions, model qwen-general; it runs on the decision-finetuned weights, not on an untouched copy of the base. Default profile: vLLM 0.32.0, bfloat16 (the precision of the reported results and of the calibration), prefix caching, eager mode, context 32768, 4 sequences, 2048 batched tokens; --fp8 loads FP8 weights to save GPU memory, changes some decisions near the decision boundary and is not calibrated. GPU memory in bfloat16: about 12 GB for this 4B model (weights plus the configured KV cache); --fp8 roughly halves the weight memory.

Request example

One state, all four question types:

curl -s localhost:8012/v1/systemone -H 'Content-Type: application/json' -d '{
  "model": "decision",
  "state": "Invoice 12/2026 for EUR 4,300 has not been paid. The payment deadline passed yesterday. The customer has paid late twice this year.",
  "questions": {
    "status": {
      "type": "choice",
      "instructions": "What is the status of the invoice?",
      "criteria": {
        "paid": "Paid",
        "overdue": "Unpaid and past the deadline",
        "not_due": "Unpaid, deadline not reached"
      }
    },
    "late": {
      "type": "noul",
      "instructions": "Has the payment deadline passed?",
      "criteria": {
        "true": "Yes",
        "false": "No"
      }
    },
    "urgency": {
      "type": "score",
      "instructions": "How urgent is collection?",
      "criteria": [
        "none",
        "low",
        "medium",
        "high",
        "critical"
      ]
    },
    "actions": {
      "type": "labels",
      "instructions": "Which actions are appropriate now?",
      "criteria": {
        "reminder": "Send a payment reminder",
        "interest": "Charge late-payment interest",
        "cancel": "Cancel the invoice"
      }
    }
  }
}'

Answers, keyed by question name: choice gives the chosen key, probabilities per option and confidence; noul gives the probability of yes; score gives the expected level (score, 0-based over the listed levels), probabilities per level, the legend and confidence; labels gives an independent probability per option and the selected keys (probability >= 0.5). Interactive schema: /docs.

Calibration

calibration.json holds one temperature per question type, fitted on the validation split only: choice T=1.625, binary T=1.625, score T=2.878, labels T=0.917. Categorical: p = softmax(log p_raw / T); labels: p = sigmoid(logit(p_raw) / T) per option. Calibration does not change argmax or 0.5-threshold decisions. bielik-one applies it by default for the standard request (one option order); --no-calibration or "temperature": 1 returns raw probabilities. It was fitted on bfloat16 outputs and is not fitted for --fp8 serving.

Data Protection and Copyright Requests

For requests concerning personal data or copyrighted content, contact biuro@speakleash.org.pl. Please include the model name and details needed to identify the material concerned.

Citation

If you use this model, please cite this model card and acknowledge the underlying base model:

@misc{wrobel2026BielikOne4Br1,
  author  = {Wróbel, Krzysztof and Ociepa, Krzysztof and Flis, Łukasz and Gwoździej, Adrian and Jezierski, Karol and Ciuciura, Igor and {SpeakLeash Team} and {Cyfronet Team}},
  title   = {Bielik-One-4B-r1},
  year    = {2026},
  version = {r1},
  url     = {https://huggingface.co/speakleash/Bielik-One-4B-r1},
  note    = {Bielik-One decision model: model card and weights}
}

Credits

Krzysztof Wróbel^SpeakLeash - decision-model design, training, evaluation and inference implementation
Krzysztof Ociepa^SpeakLeash - consultations
Qwen Team - development of the underlying Qwen3.5-4B base model.

We thank the entire SpeakLeash team for their commitment to the Bielik project and the collaboration between the open-science SpeakLeash project and the HPC center ACK Cyfronet AGH. We gratefully acknowledge the contributions of: Sebastian Kondracki, Marek Magryś, Sonia Staniek, Waldemar Boszko, Maria Czarkowska, Jacek Chwiła, Kuba Sołtys, Dominika Basaj, Remigiusz Kinas, Marcin Dąbrowski, Anna Przybył, Agnieszka Ratajska, Daria Bartkowiak, Witold Wydmański, Jan Sowa, Grzegorz Anioł, Bartosz Bartnicki, and many other wonderful researchers and enthusiasts of the AI world.

Contact Us

If you have any questions or suggestions, please use the discussion tab. If you want to contact us directly, join our Discord SpeakLeash.

Acknowledgements

We gratefully acknowledge Polish high-performance computing infrastructure PLGrid (HPC Center: ACC Cyfronet AGH) for providing computer facilities and support within computational grant no. [PLG/2026/019559].

This work was supported by the Gaia AI Factory project, funded by the European Union under Grant Agreement No. 101314359 through the EuroHPC Joint Undertaking (EuroHPC JU).