exp018-dpo-merged

SFT + DPO merged model. Full 16-bit weights, no adapter loading required.

Training Pipeline

1. SFT: tomofusa/exp015-blend-h-lora
2. DPO: u-10bei/dpo-dataset-qwen-cot (1 epoch, lr=5e-07, beta=0.01)

DPO Configuration

• Learning rate: 5e-07
• Beta: 0.01
• Loss type: ipo
• LoRA: r=64, alpha=128
• Max length: 1024