Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
EEVE-Korean-10.8B-DPO-v1.0 – AI Model by ai-human-lab | AlphaNeural AI
You can deploy this model and start earning money today!
ai-human-lab
/
EEVE-Korean-10.8B-DPO-v1.0
like
0
transformers
pytorch
safetensors
llama
text-generation
conversational
apache-2.0
autotrain_compatible
text-generation-inference
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
About the Model
This model is a fine-tuned version of yanolja/EEVE-Korean-10.8B-v1.0, which is a Korean vocabulary-extended version of upstage/SOLAR-10.7B-v1.0. Specifically, we utilized Direct Preference Optimization (DPO) through the use of Axolotl.
