Llama3.1 70B instruct를 unsloth로 dpo 파인튜닝했습니다.
데이터셋 : https://github.com/DopeorNope-Lee/Ko-Fine-tuning_DataGen/tree/main
Contact : cgh@tnap.co.kr
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support