Instructions to use sedatyilmazer/kanunlar with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sedatyilmazer/kanunlar with Transformers:

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

pipe = pipeline("text-generation", model="sedatyilmazer/kanunlar")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sedatyilmazer/kanunlar")
model = AutoModelForCausalLM.from_pretrained("sedatyilmazer/kanunlar")
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

vLLM

How to use sedatyilmazer/kanunlar with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/sedatyilmazer/kanunlar

SGLang

How to use sedatyilmazer/kanunlar 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 "sedatyilmazer/kanunlar" \
    --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": "sedatyilmazer/kanunlar",
		"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 "sedatyilmazer/kanunlar" \
        --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": "sedatyilmazer/kanunlar",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sedatyilmazer/kanunlar with Docker Model Runner:
```
docker model run hf.co/sedatyilmazer/kanunlar
```

Model Card for Model ID

Model Details

Model Description

This model is a fineuned qwen3.5:9B with a turkish law dataset (sedatyilmazer/Kanunlar)

Developed by: Sedat YILMAZER
Model type: QWEN3.5
Language(s) (NLP): Turkish
Finetuned from model : QWEN3.5:9B

Model Sources [optional]


!pip install git+https://github.com/huggingface/transformers.git -U
!pip install accelerate peft -U

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

# --- YAPILANDIRMA ---
# Yeni oluşturduğun modelin Hugging Face ID'si
model_id = "sedatyilmazer/kanunlar"

def run_kanunlar_inference():
    print(f"🚀 Blackwell GPU üzerinde '{model_id}' yükleniyor...")

    try:
        # 1. Tokenizer ve Model Yükleme
        # Blackwell mimarisi için torch_dtype=torch.bfloat16 en verimli tercihtir.
        tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
        
        model = AutoModelForCausalLM.from_pretrained(
            model_id,
            torch_dtype=torch.bfloat16,
            device_map="auto",
            trust_remote_code=True
        )

        print("✅ Model başarıyla yüklendi! Sorgu işleniyor...")

        # 2. Test Sorusu (Prompt)
        # Qwen modelleri genellikle ChatML formatını (<|im_start|>) sever.
        user_query = "KVKK nedir?"
        
        prompt = f"<|im_start|>user\n{user_query}<|im_end|>\n<|im_start|>assistant\n"
        inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

        # 3. Yanıt Üretme (Generation)
        with torch.no_grad():
            output_ids = model.generate(
                **inputs,
                max_new_tokens=32000,   # Blackwell'de bellek sorunu olmadığı için yüksek tutabilirsin
                temperature=0.3,       # Hukuk metinlerinde tutarlılık için düşük sıcaklık
                top_p=0.9,
                repetition_penalty=1.1,
                do_sample=True,
                pad_token_id=tokenizer.eos_token_id
            )

        # 4. Çıktıyı Decode Etme
        response = tokenizer.decode(output_ids[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True)
        
        print("\n" + "="*60)
        print(f"SORU: {user_query}")
        print("-" * 60)
        print(f"KANUNLAR YANITI:\n\n{response}")
        print("="*60)

    except Exception as e:
        print(f"❌ HATA: {str(e)}")

# Testi Başlat
run_kanunlar_inference()

Training Data

sedatyilmazer/Kanunlar

Downloads last month: 3

Safetensors

Model size

9B params

Tensor type

BF16