Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
komt_DPOv3 – AI Model by ENERGY-DRINK-LOVE | AlphaNeural AI | AlphaNeural AI
You can deploy this model and start earning money today!
ENERGY-DRINK-LOVE
/
komt_DPOv3
like
0
transformers
safetensors
llama
text-generation
trl
dpo
generated_from_trainer
2305.18290
davidkim205/komt-solar-10.7b-sft-v5
finetune
cc-by-4.0
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
ENERGY-DRINK-LOVE/komt_DPOv3
Our Team
Youjin Chung
Jingyeom Kim
Model
Base Model
davidkim205/komt-solar-10.7b-sft-v5
Hardware and Software
Hardware: A100 * 8 for training our model
Deepspeed library & Huggingface TRL Trainer
Dataset
DPO_dataset
자체 제작 dpo dataset(AI-hub dataset 활용)
OpenOrca DPO 등 영어 데이터셋 번역(ENERGY-DRINK-LOVE/translate_share_gpt_dedup_llama_SFT_1024, 자체모델 활용)
Training Method
DPO
Benchmark
Ko LM Eval Harness
Ko-LLM-Leaderboard
(240316기준 4등)
image/png
Average
Ko-ARC
Ko-HellaSwag
Ko-MMLU
Ko-TruthfulQA
Ko-CommonGen V2
61.20
57.51
70.33
53.34
68.49
56.32
