Instructions to use bertuginal/KiviElektronik-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bertuginal/KiviElektronik-1.5B with Transformers:

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

pipe = pipeline("text-generation", model="bertuginal/KiviElektronik-1.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bertuginal/KiviElektronik-1.5B")
model = AutoModelForCausalLM.from_pretrained("bertuginal/KiviElektronik-1.5B", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

PEFT
How to use bertuginal/KiviElektronik-1.5B with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bertuginal/KiviElektronik-1.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bertuginal/KiviElektronik-1.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bertuginal/KiviElektronik-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bertuginal/KiviElektronik-1.5B

SGLang

How to use bertuginal/KiviElektronik-1.5B 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 "bertuginal/KiviElektronik-1.5B" \
    --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": "bertuginal/KiviElektronik-1.5B",
		"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 "bertuginal/KiviElektronik-1.5B" \
        --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": "bertuginal/KiviElektronik-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bertuginal/KiviElektronik-1.5B with Docker Model Runner:
```
docker model run hf.co/bertuginal/KiviElektronik-1.5B
```

Kivi Elektronik - Müşteri Hizmetleri Asistanı (Qwen2.5-1.5B-Instruct)

Bu model, kurgusal e-ticaret markası Kivi Elektronik için müşteri hizmetleri süreçlerini otomatize etmek amacıyla Qwen2.5-1.5B-Instruct taban modeli temel alınarak LoRA (PEFT) yöntemiyle ince ayardan (fine-tuning) geçirilmiş özel bir sohbet asistanıdır.

Model Details

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Developed by: bertuginal
Funded by: Kivi Elektronik (Personal Project)
Shared by: bertuginal
Model type: Causal Language Model / E-commerce Conversational Agent
Language(s): Türkçe (Turkish)
License: Apache-2.0
Finetuned from model: Qwen/Qwen2.5-1.5B-Instruct

Model Sources

Repository: Hugging Face Model Hub
Paper: Qwen2.5 Technical Report
Demo: Space Integration (Included in repo)

Direct Use

Kivi Elektronik müşterilerinin ürün sorguları, kargo ücretleri, iade/değişim koşulları ve sipariş süreçleriyle ilgili sorularına otomatik, nazik ve kurumsal yanıtlar vermek için doğrudan kullanılabilir.

Downstream Use

E-ticaret web sitelerine (Shopify, WordPress/WooCommerce vb.) canlı destek widget'ı olarak entegre edilebilir veya RAG sistemlerine alt katman olarak eklenebilir.

Out-of-Scope Use

Mağaza dışı genel kültür soruları, finansal/tıbbi tavsiyeler ve Kivi Elektronik politikalarıyla çelişen senaryolar için uygun değildir.

Bias, Risks, and Limitations

Model küçük ölçekli (1.5B) bir taban modelden türetildiği için nadiren de olsa halüsinasyon görebilir. Mağaza kuralları dışındaki durumlarda canlı desteğe yönlendirme yapacak şekilde yapılandırılmıştır.

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Prompt yapılandırmasında sağlanan sistem kurallarına bağlı kalması önerilir.

How to Get Started with the Model

Use the code below to get started with the model.

from llama_cpp import Llama

llm = Llama(
    model_path="kivi-elektronik-1.5b.gguf",
    n_ctx=2048,
    n_threads=4
)

prompt = """<|im_start|>system
Sen Kivi Elektronik müşteri hizmetleri asistanısın. 1000 TL üzerine kargo ücretsizdir.
<|im_end|>
<|im_start|>user
Kargo ücreti ne kadar?
<|im_end|>
<|im_start|>assistant
"""

output = llm(prompt, max_tokens=256, stop=["<|im_end|>"], temperature=0.7)
print(output["choices"][0]["text"])

Downloads last month: 303

Safetensors

Model size

2B params

Tensor type

F16

Model tree for bertuginal/KiviElektronik-1.5B

Adapters

1 model