Lucas Simonnet

derko83 's models 16

Sort:  Recently updated

derko83/MNLP_M3_dpo_model

Text Generation • 0.6B • Updated Jun 10 • 7

derko83/dpo_full_bf16_5e-7_0.1_linear_v2_test_test_test

Text Generation • 0.6B • Updated Jun 10 • 3

derko83/test_subset_best_modele

Text Generation • 0.6B • Updated Jun 9 • 4

derko83/dpo_end_4400

0.6B • Updated Jun 9 • 5

derko83/dpo_end_2400

0.6B • Updated Jun 9 • 4

derko83/sft_plus_dpo_full_5e-7_0.1_linear

0.6B • Updated Jun 6 • 5

derko83/dpo_full_5e-7_0.1_linear

0.6B • Updated Jun 5 • 4

derko83/dpo_eval_3e-6_0.05_v2

0.6B • Updated Jun 4 • 8

derko83/dpo_eval_3e-6_0.05

Updated Jun 4

derko83/1024_max_tok_dpo_v2

0.6B • Updated Jun 3 • 6

derko83/1024_max_tok_dpo_v1

0.6B • Updated Jun 3 • 6

derko83/512_max_tok_dpo_v2

0.6B • Updated Jun 3 • 6

derko83/512_max_tok_dpo

0.6B • Updated Jun 3 • 4

derko83/dpo_longstep_3_4_4

0.6B • Updated Jun 2 • 3

derko83/weights_for_naj

0.6B • Updated Jun 2 • 5

derko83/MNLP_M2_dpo_model

0.6B • Updated May 27 • 5