metadata
license: apache-2.0
An experimental DPO finetune of SmartTinyLlama with Alpaca-QLoRA Datasets Trained on bagel style dpo datasets Prompt Template Uses chatml style prompt template
license: apache-2.0
An experimental DPO finetune of SmartTinyLlama with Alpaca-QLoRA Datasets Trained on bagel style dpo datasets Prompt Template Uses chatml style prompt template