TwinDoc's picture
Update README.md
1163d0a verified
metadata
language:
  - ko
  - en
library_name: transformers
license: cc-by-nc-sa-4.0
pipeline_tag: text-generation
tags:
  - pytorch

Model Description

K-S 고객사 ν”„λ‘œμ νŠΈ μ‹œ μƒμ„±ν•œ RAG 데이터셋을 ν™œμš©ν•˜μ—¬ Supervised Fine-Tuning(a.k.a SFT) ν•™μŠ΅ν•œ λͺ¨λΈμž…λ‹ˆλ‹€. ν•™μŠ΅ 데이터셋은 λ³΄μ•ˆμ— μ˜ν•΄ κ³΅κ°œν•˜μ§€ μ•ŠμŠ΅λ‹ˆλ‹€.

About the Model

  • Name: TwinDoc/RedWhale-tv-10.8B-sft-k

  • Finetuned from model: TwinDoc/RedWhale-tv-10.8B-v1.0

  • Train Datasets: private

  • Developed by: μ• μžμΌμ†Œλ‹€ (AGILESODA)

  • Model type: llama

  • Language(s) (NLP): ν•œκ΅­μ–΄

  • License: cc-by-nc-sa-4.0

  • train setting

    • Lora r, alpha : 32, 32
    • Dtype : bf16
    • Epoch : 5
    • Learning rate : 1e-5
    • Global batch : 1
    • Context length : 4096
  • inference setting

    • BOS id : 1
    • EOS id : 2
    • Top-p : 0.95
    • Temperature : 0.01

prompt template

### User: 당신은 인곡지λŠ₯ λΉ„μ„œμž…λ‹ˆλ‹€. μ‚¬μš©μžκ°€ μ—¬λŸ¬λΆ„μ—κ²Œ 과제λ₯Ό μ€λ‹ˆλ‹€. λ‹Ήμ‹ μ˜ λͺ©ν‘œλŠ” κ°€λŠ₯ν•œ ν•œ μΆ©μ‹€ν•˜κ²Œ μž‘μ—…μ„ μ™„λ£Œν•˜λŠ” κ²ƒμž…λ‹ˆλ‹€. μž‘μ—…μ„ μˆ˜ν–‰ν•˜λŠ” λ™μ•ˆ λ‹¨κ³„λ³„λ‘œ μƒκ°ν•˜κ³  단계λ₯Ό μ •λ‹Ήν™”ν•˜μ„Έμš”. User의 질문이 주어지면 κ³ ν’ˆμ§ˆμ˜ 닡변을 λ§Œλ“€μ–΄μ£Όμ„Έμš”.
원문: {CONTEXT}
질문: 원문을 μ°Έκ³ ν•˜μ—¬ λ‹΅λ³€ν•˜μ„Έμš”. {QUESTION}
 ### Assistant: {ANSWER}

License

The content of this project, created by AGILESODA, is licensed under the Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).

Citation

@misc{vo2024redwhaleadaptedkoreanllm,
      title={RedWhale: An Adapted Korean LLM Through Efficient Continual Pretraining}, 
      author={Anh-Dung Vo and Minseong Jung and Wonbeen Lee and Daewoo Choi},
      year={2024},
      eprint={2408.11294},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2408.11294}, 
}

Built with:

AgileSoda TwinDoc Icon