ma921/ministral_h_dpo_oasst1-english_noise40_epoch5_gamma0.5_beta1
Updated • 1
Masaki Adachi
ma921
·
AI & ML interests
None yet
Organizations
None yet
models 217
ma921/ministral_h_dpo_oasst1-english_noise40_epoch5_gamma0.01
Updated
ma921/ministral_h_dpo_oasst1-english_noise40_epoch5_gamma0.1
Updated
ma921/phi2_dr_dpo_hh-rlhf-filtered-epoch1_noise0_epoch1_gamma2
Text Generation • 3B • Updated • 1
ma921/phi2_dpo_hh-rlhf-filtered-rejected_noise0_epoch1_gamma2
Text Generation • 3B • Updated • 1
ma921/ministral_h_dpo_oasst1-english_noise40_epoch5_gamma0.5
Updated
ma921/ministral_h_dpo_oasst1-english_noise40_epoch5_gamma10
Updated
ma921/phi2_dr_dpo_hh-rlhf_noise0_epoch2_gamma2
Text Generation • 3B • Updated • 1
ma921/ministral_h_dpo_oasst1-english_noise40_epoch5_adam8bit-lr1e-6
Updated
ma921/ministral_h_dpo_oasst1-english_noise40_epoch5_lr1e-6
Updated
datasets 61
ma921/golden-hh-tokenized-gpt2_noise0
Viewer • Updated • 12.1k • 4
ma921/hh-rlhf-test-filtered-epoch2-tokenized-phi2_noise0
Viewer • Updated • 1.81k • 3
ma921/hh-rlhf-test-tokenized-phi2_noise0
Viewer • Updated • 2.53k • 4
ma921/hh-rlhf-filtered-rejected-tokenized-phi2_noise0
Viewer • Updated • 12.2k • 2
ma921/hh-rlhf-filtered-epoch2-tokenized-phi2_noise0
Viewer • Updated • 36.2k • 2
ma921/oasst1-english-tokenized-ministral_noise40
Viewer • Updated • 6.86k • 3
ma921/oasst1-english-tokenized-ministral_noise0
Viewer • Updated • 6.86k • 8
ma921/hh-rlhf-filtered-epoch1-tokenized-phi2_noise0
Viewer • Updated • 36k • 3
ma921/hh-rlhf-tokenized-phi2_noise0
Viewer • Updated • 48.2k • 3
ma921/oasst1-english-tokenized-qwen2.5_noise40
Viewer • Updated • 6.86k • 4