CorticalStack/pastiche-crown-clown-7b-dare-dpo

<img src="pastiche-crown-clown.png" alt="Pastiche crown clown logo" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>

CorticalStack/pastiche-crown-clown-7b-dare-dpo

CorticalStack/pastiche-crown-clown-7b-dare-dpo is a DPO fine-tuned version of CorticalStack/pastiche-crown-clown-7b-dare using the jondurbin/truthy-dpo-v0.1 dataset.

LoRA

• —r: 16
• —LoRA alpha: 16
• —LoRA dropout: 0.05

Training arguments

• —Batch size: 4
• —Gradient accumulation steps: 4
• —Optimizer: pagedadamw32bit
• —Max steps: 200
• —Learning rate: 5e-05
• —Learning rate scheduler type: cosine
• —Beta: 0.1
• —Max prompt length: 1024
• —Max length: 1536