Gemma2-2B-IT-Sms-Verification_Code_Extraction

SMS에서 인증번호를 추출 하는 gemma2 SFT 모델

• 모바일 앱에서 사용하기 위한 Quantization 모델은 아래 참조.

  • https://huggingface.co/sg2023/Gemma2-2B-IT-Sms-Verification_Code_Extraction-int8-tflite

• Input / Output

  • "본인인증번호는 315611 입니다. 정확히 입력해주세요." -> 315611
  • "안녕하세요" -> 0

from transformers import Gemma2ForCausalLM, AutoTokenizer

repo_id = "sg2023/Gemma2-2B-IT-Sms-Verification_Code_Extraction"
tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = Gemma2ForCausalLM.from_pretrained(repo_id)
model.eval()

prompt = "본인인증번호는 315611 입니다. 정확히 입력해주세요."
request_template = [{"role": "user", "content": prompt}]
response_template = tokenizer.apply_chat_template(request_template, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(response_template, return_tensors="pt").to(model.device)
input_ids = inputs["input_ids"][0]  # Tensor shape: (seq_len,)
input_len = input_ids.shape[0]

outputs = model.generate(**inputs, max_new_tokens=64)[0]
outputs = outputs[input_len:]
outputs = tokenizer.decode(outputs, skip_special_tokens=True)

print(outputs)  # 315611

Gemma 2 model card

Model Page: Gemma

Resources and Technical Documentation:

• Responsible Generative AI Toolkit
• Gemma on Kaggle
• Gemma on Vertex Model Garden

Terms of Use: Terms

Authors: Google