Instructions to use keeeeesz/gemma-civil-code-pl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use keeeeesz/gemma-civil-code-pl with Transformers:

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

pipe = pipeline("text-generation", model="keeeeesz/gemma-civil-code-pl")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("keeeeesz/gemma-civil-code-pl")
model = AutoModelForMultimodalLM.from_pretrained("keeeeesz/gemma-civil-code-pl", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use keeeeesz/gemma-civil-code-pl with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/keeeeesz/gemma-civil-code-pl

SGLang

How to use keeeeesz/gemma-civil-code-pl 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 "keeeeesz/gemma-civil-code-pl" \
    --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": "keeeeesz/gemma-civil-code-pl",
		"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 "keeeeesz/gemma-civil-code-pl" \
        --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": "keeeeesz/gemma-civil-code-pl",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use keeeeesz/gemma-civil-code-pl with Docker Model Runner:
```
docker model run hf.co/keeeeesz/gemma-civil-code-pl
```

gemma-civil-code-pl

Model Gemma 3 (4B) dostrojony do wiedzy z Kodeksu Cywilnego, odpowiadający na pytania prawne

Opis modelu

Model bazuje na Gemma 3 (4B) i został dostrojony do odpowiadania na pytania dotyczące Kodeksu Cywilnego. Wykorzystano dane z artykułów Kodeksu Cywilnego wraz z interpretacjami i przykładami zastosowania.

Przykładowe użycie

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Załaduj model i tokenizer
model_name = "keeeeesz/gemma-civil-code-pl"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    device_map="auto",
)

# Formatuj pytanie w formacie chatowym
def format_prompt(pytanie):
    return f"<start_of_turn>user\n{pytanie}<end_of_turn>"

# Generuj odpowiedź
pytanie = "Co stanowi artykuł 5 Kodeksu cywilnego?"
prompt = format_prompt(pytanie)

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
    **inputs,
    max_new_tokens=512,
    do_sample=True,
    temperature=0.7,
    top_p=0.9,
)

# Wyodrębnij odpowiedź
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Downloads last month: 8

Safetensors

Model size

4B params

Tensor type

F16

Model tree for keeeeesz/gemma-civil-code-pl

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Finetuned

(751)

this model