Instructions to use slovak-nlp/Qwen3-14B-sk with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use slovak-nlp/Qwen3-14B-sk with Transformers:

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

pipe = pipeline("text-generation", model="slovak-nlp/Qwen3-14B-sk")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("slovak-nlp/Qwen3-14B-sk")
model = AutoModelForCausalLM.from_pretrained("slovak-nlp/Qwen3-14B-sk", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use slovak-nlp/Qwen3-14B-sk with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "slovak-nlp/Qwen3-14B-sk"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "slovak-nlp/Qwen3-14B-sk",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/slovak-nlp/Qwen3-14B-sk

SGLang

How to use slovak-nlp/Qwen3-14B-sk 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 "slovak-nlp/Qwen3-14B-sk" \
    --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": "slovak-nlp/Qwen3-14B-sk",
		"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 "slovak-nlp/Qwen3-14B-sk" \
        --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": "slovak-nlp/Qwen3-14B-sk",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use slovak-nlp/Qwen3-14B-sk with Docker Model Runner:
```
docker model run hf.co/slovak-nlp/Qwen3-14B-sk
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Qwen3-14B-sk

Qwen3-14B-sk is a Slovak language version of the Qwen3-14B large language model with 14 billion parameters.

Model Details

Qwen3-14B-sk is a Slovak language model obtained by full parameter fine-tuning of the Qwen3-14B large language model. The model was developed in collaboration of Institute of Artificial Intelligence, Faculty of Electrical Engineering and Informatics, Technical University of Košice; Centre of Social and Psychological Sciences of the Slovak Academy of Sciences, Ľ. Štúr Institute of Linguistics, Slovak Academy of Sciences and ČZ, o.z. The model was fine-tuned using the following datasets:

Data from the "Araneum Slovacum VII Maximum" web corpus, provided by the UNESCO Chair in Plurilingual and Multicultural Communication at Comenius University and the Ľudovít Štúr Institute of Linguistics.
Pre-processed data from the Dictionary of the Slovak Language, provided by the Ľudovít Štúr Institute of Linguistics.
Data from the Encyclopaedia Beliana, provided by the Encyclopedic Institute of the Slovak Academy of Sciences.

Model overview

Language: Slovak
License: Apache license 2.0
Finetuned from model: Qwen/Qwen3-14B
Authors:
- Peter Bednár, Institute of Artificial Intelligence, Faculty of Electrical Engineering and Informatics, Technical University of Košice
- Marek Dobeš, Centre of Social and Psychological Sciences of the Slovak Academy of Sciences and ČZ o.z.
- Radovan Garabík, Ľ. Štúr Institute of Linguistics, Slovak Academy of Sciences, supported by DiusAI a. s.

Limitations

The model occasionally exhibits repetitive behavior in its responses. Hallucination rates are comparable to other models of similar scale. Please note that no output moderation or safety filtering techniques have been applied.

Supported by

The Qwen3-14B-sk model was trained using high-performance computing infrastructure operated by CINECA and awarded through the National Leonardo access call by the Computing Centre of the Slovak Academy of Sciences, as well as the PERUN supercomputer provided by Technical University of Košice.

Downloads last month: 453

Safetensors

Model size

15B params

Tensor type

F32

Model tree for slovak-nlp/Qwen3-14B-sk

Base model

Qwen/Qwen3-14B-Base

Finetuned

Qwen/Qwen3-14B

Finetuned

(320)

this model

Adapters

1 model

Quantizations

5 models