Model Description
K-S κ³ κ°μ¬ νλ‘μ νΈ μ μμ±ν RAG λ°μ΄ν°μ μ νμ©νμ¬ Supervised Fine-Tuning(a.k.a SFT) νμ΅ν λͺ¨λΈμ λλ€. νμ΅ λ°μ΄ν°μ μ 보μμ μν΄ κ³΅κ°νμ§ μμ΅λλ€.
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 μμΌμλ€ (AGILESODA)
Model type: llama
Language(s) (NLP): νκ΅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: λΉμ μ μΈκ³΅μ§λ₯ λΉμμ
λλ€. μ¬μ©μκ° μ¬λ¬λΆμκ² κ³Όμ λ₯Ό μ€λλ€. λΉμ μ λͺ©νλ κ°λ₯ν ν μΆ©μ€νκ² μμ
μ μλ£νλ κ²μ
λλ€. μμ
μ μννλ λμ λ¨κ³λ³λ‘ μκ°νκ³ λ¨κ³λ₯Ό μ λΉννμΈμ. Userμ μ§λ¬Έμ΄ μ£Όμ΄μ§λ©΄ κ³ νμ§μ λ΅λ³μ λ§λ€μ΄μ£ΌμΈμ.
μλ¬Έ: {CONTEXT}
μ§λ¬Έ: μλ¬Έμ μ°Έκ³ νμ¬ λ΅λ³νμΈμ. {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:
- Downloads last month
- 0
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Collection including TwinDoc/RedWhale-tv-10.8B-sft-k
Collection
6 items
β’
Updated