Hugging Face's logo

UICHEOL-HWANG
/
Dacon-contest-obfuscation-ko-gemma-7b

Text Generation
Transformers
Safetensors
Korean
gemma
text-generation-inference
Inference Endpoints
Model card Files Community

Dacon 난독화 데이터셋 파인튜닝

  • 원본 대회 정보
  • Dacon image/png

대회 링크 https://dacon.io

  • Machine Spec
  • GCP V100

    • 실행 Spec

      • batch_size : 4, max_length : 512, trl, peft, BitsAndBytesConfig, bfloat16으로 실행
      • total loss : 2.1

    • 위 모델의 데이터는 Dacon을 통해 제공 받았으며, 해당 모델은 비영리적으로 사용할 예정 입니다(포트폴리오용, 시험 제출용)

    • beomi/gemma-ko-7b fine-tune

Downloads last month
48
Safetensors
Model size
8.54B params
Tensor type
FP16
·
Inference Providers NEW
Text Generation
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for UICHEOL-HWANG/Dacon-contest-obfuscation-ko-gemma-7b

Base model

beomi/gemma-ko-7b
Finetuned
(4)
this model