Gemma3-1B-LOMO-Shipbuilding-Marine

Model Description

This model is a fine-tuned version of the Gemma3-1B model. It has been specifically adapted for the shipbuilding and marine domain using the LOMO (LOw-Memory Optimization) methodology. It was trained on a dataset of 5,000 specialized terms.

이 모델은 Gemma3-1B를 기반으로, 조선해양 분야의 전문 용어에 특화하여 파인튜닝한 모델입니다. LOMO (LOw-Memory Optimization) 방법론을 사용하여 학습되었습니다. 5,000개의 전문 용어 데이터셋으로 학습되었습니다.

How to Use

You can use this model with the transformers library:

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "naisksh32/Gemma3-1B-LOMO-Shipbuilding-Marine"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Example usage
prompt = "해양플랜트의 주요 설비는 무엇인가요?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=128)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Note: Please replace "naisksh32/Gemma3-1B-LOMO-Shipbuilding-Marine" with the actual repository name after you upload the model.

Training Details

• Base Model: Gemma3-1B
• Fine-tuning Method: LOMO (LOw-Memory Optimization)
• Dataset: A custom dataset containing 5,000 terms and related texts from the shipbuilding and marine industry.
• Domain: Shipbuilding and Marine

Disclaimer

This model is a research artifact and may have limitations. It is optimized for specialized terminology and its performance on general-purpose tasks may vary.