mmmanuel/SFT_nochat_FULL_DATA
Text Generation • 0.6B • Updated • 4
manuel curnis
mmmanuel
·
AI & ML interests
None yet
Organizations
None yet
models 27
mmmanuel/lr_1e_06_beta_0p1_epochs_1
Text Generation • 0.6B • Updated • 1
mmmanuel/lr_1e_06_beta_0p05_epochs_1
Text Generation • 0.6B • Updated • 1
mmmanuel/lr_1e_06_beta_0p01_epochs_1
Text Generation • 0.6B • Updated • 1
mmmanuel/lr_5e_05_beta_0p2_epochs_1
Text Generation • 0.6B • Updated • 1
mmmanuel/lr_5e_05_beta_0p1_epochs_1
Text Generation • 0.6B • Updated • 1
mmmanuel/lr_5e_05_beta_0p05_epochs_1
Text Generation • 0.6B • Updated • 1
mmmanuel/lr_1e_05_beta_0p05_epochs_1
Text Generation • 0.6B • Updated • 1
mmmanuel/lr_1e_05_beta_0p2_epochs_1
Text Generation • 0.6B • Updated • 1
mmmanuel/len_norm_dpo
Text Generation • 0.6B • Updated • 1
datasets 16
mmmanuel/final
Updated • 3
mmmanuel/SFT_dataset
Viewer • Updated • 255k • 2
mmmanuel/big_pne_not_used
Viewer • Updated • 93.5k • 4
mmmanuel/GTP_generated_ultimate
Viewer • Updated • 21k • 4
mmmanuel/MNLP_M3_dpo_dataset
Viewer • Updated • 84.1k • 4
mmmanuel/stackexchange_dpo_stem
Viewer • Updated • 9.79k • 3
mmmanuel/DPO_complete_dataset
Viewer • Updated • 78.8k • 7
mmmanuel/GTP_generated_3300
Viewer • Updated • 6.3k • 3
mmmanuel/filtered_Math-Step-DPO-10K
Viewer • Updated • 10.8k • 3
mmmanuel/cleaned-math-preference-dpo
Viewer • Updated • 2.42k • 3