You can deploy this model and start earning money today!

UICHEOL-HWANG/
EcomGen-Gemma3-4B

Name: EcomGen-Gemma3-4B
Rating: 2.5 (8 reviews)

text-generation-inference

unsloth

conversational

unsloth/gemma-3-4b-it-unsloth-bnb-4bit

finetune

apache-2.0

endpoints_compatible

Views

No views yet

Uploaded finetuned model

Developed by: UICHEOL-HWANG
License: apache-2.0
Finetuned from model : unsloth/gemma-3-4b-it-unsloth-bnb-4bit

This gemma3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

사용 방법

연산 이슈가 있어 TorchDynamo를 먼저 비활성화 시키고 진행 시켜야합니다.

python

import os
os.environ["TORCHDYNAMO_DISABLE"] = "1"

python

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

# Model and Tokenizer Loading
model_name = "UICHEOL-HWANG/EcomGen-Gemma3-4B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

def generate_product_description(texts):
    """
    Generate product description using EcomGen-Gemma3-4B
    
    Args:
        texts (str): Input prompt for product description generation
    
    Returns:
        str: Generated product description
    """
    # Format the input using chat template
    messages = [{
        "role": "user",
        "content": [{"type": "text", "text": texts}]
    }]
    
    text = tokenizer.apply_chat_template(
        messages,
        add_generation_prompt=True,
        tokenize=False 
    )
    
    inputs = tokenizer([text], return_tensors="pt").to(model.device)
    
    # Generate response
    with torch.no_grad():
        outputs = model.generate(
            **inputs,
            max_new_tokens=512,
            temperature=1.0, 
            top_p=0.95, 
            top_k=64,        
            do_sample=True,
            pad_token_id=tokenizer.pad_token_id,
            eos_token_id=tokenizer.eos_token_id
        )
    
    # Decode the response (excluding the input prompt)
    response = tokenizer.decode(
        outputs[0][inputs['input_ids'].shape[-1]:], 
        skip_special_tokens=True
    )
    
    return response.strip()

# Example Usage
if __name__ == "__main__":
    # Example 1: Product description generation
    prompt = """상품명: 프리미엄 유기농 쌀 10kg
카테고리: 식품 > 쌀·잡곡
가격: 45,000원
핵심 키워드: 유기농, 쌀, 농부, 정성, 고가, 품질, 안전, 가족, 건강
작성 톤: 신뢰감_있는_전문가_톤 (품질 중심, 프리미엄 상품 강조)"""
    
    result = generate_product_description(prompt)
    print("Generated Product Description:")
    print(result)
    
    # Example 2: Different product category
    prompt2 = """상품명: 무선 블루투스 이어폰 AirPods Pro
카테고리: 전자제품 > 오디오
가격: 329,000원
핵심 키워드: 무선, 블루투스, 노이즈캔슬링, 프리미엄, 애플, 고음질
작성 톤: 트렌디한_젊은_톤 (기술과 라이프스타일 강조)"""
    
    result2 = generate_product_description(prompt2)
    print("\nGenerated Product Description 2:")
    print(result2)