etri-xainlp/SOLAR-10.7B-sft-dpo-v1

Model Details

Model Developers ETRI xainlp team

Input text only.

Output text only.

Model Architecture

Base Model davidkim205/nox-solar-10.7b-v4

Training Dataset

• sft+lora: 1,821,734 cot set

• dpo+lora: 221,869 user preference set

• We use A100 GPU 80GB * 8, when training.