ma921/phi-2-sft-hh-rlhf download history
ma921/phi-2-sft-hh-rlhf is a 2.8B-parameter text generation model by ma921. In the last 30 days it was downloaded 11 times (6 in the last 7 days), and 167 times in total.
It ranks #708,164 on the Hub by monthly downloads and #263,235 among text generation models.
It has 0 likes.
It is a fine-tune of microsoft/phi-2.
9 models build on phi-2-sft-hh-rlhf: 0 quantized, 9 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 74 times in the last 30 days. See the phi-2-sft-hh-rlhf galaxy.
Most downloaded derivatives
- ma921/phi2_r_dpo_hh-rlhf-filtered-epoch1_noise0_epoch1_gamma2 (finetune), 8 downloads in 30 days
- ma921/phi2_dpo_hh-rlhf-filtered-epoch1_noise0_epoch1_gamma2 (finetune), 7 downloads in 30 days
- ma921/phi2_h_dpo_hh-rlhf_noise0_epoch1_gamma2 (finetune), 7 downloads in 30 days
- ma921/phi2_dpo_hh-rlhf_noise0_epoch1_gamma2 (finetune), 6 downloads in 30 days
- ma921/phi2_dr_dpo_hh-rlhf_noise0_epoch1_gamma2 (finetune), 6 downloads in 30 days
- ma921/phi2_dr_dpo_hh-rlhf-filtered-epoch1_noise0_epoch1_gamma2 (finetune), 4 downloads in 30 days