Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
KoLIMA-5.8b – AI Model by heegyu | AlphaNeural AI
You can deploy this model and start earning money today!
heegyu
/
KoLIMA-5.8b
like
0
transformers
pytorch
gpt_neox
text-generation
apache-2.0
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
polyglot-ko-5.8b를 lora로 학습 후 가중치 병합. ko-lima 데이터 사용. 10에폭 1e-4 -> 1e-5 cosine decay. 배치 128, 최대시퀀스길이 2048
