# DPO Reinforcement Learning

A fine-tuned version based on Minbyul/selfbiorag-7b-wo-kqa_golden-iter-dpo-step3-filtered, trained using the HuggingFace MedLFQA dataset (excluding kqa_golden) with Direct Preference Optimization (DPO)

A 7B-parameter large language model co-created by IkariDev and Undi, optimized with DPO training

DPOpenHermes 7B v2 is the second RL fine-tuned model based on OpenHermes-2.5-Mistral-7B, utilizing Direct Preference Optimization (DPO) for reinforcement learning with the Intel/orca_dpo_pairs and allenai/ultrafeedback_binarized_cleaned preference datasets.

CausalLM/14B-DPO-α is a large-scale causal language model supporting Chinese and English text generation tasks, with outstanding performance in MT-Bench evaluations.