valerielucro/mistral_gsm8k_preference_dataset_v2_beta_1
0
second iteration Qlora with DPO on full gsm8k preference dataset version 2.1 and 1 epoch and rank 64, beta 0.1
second iteration Qlora with DPO on full gsm8k preference dataset version 2.1 and 1 epoch and rank 64, beta 0.1
initial commit
