AI & ML interests
None yet
Organizations
None yet
vidyc/direct_dpo_gemini_m1_open_trl_20k_step_dpo_no_ref_more
Text Generation
•
0.6B
•
Updated
•
7
Text Generation
•
0.6B
•
Updated
•
6
vidyc/direct_dpo_gemini_m1_open_trl_20k_step_dpo_no_ref
Text Generation
•
0.6B
•
Updated
•
7
vidyc/direct_dpo_gemini_m1_open_trl_20k_step_dpo
Text Generation
•
0.6B
•
Updated
•
7
vidyc/sft_dpo_gemini_m1_open_trl_20k_tulu_step_dpo
Text Generation
•
0.6B
•
Updated
•
7
vidyc/sft_dpo_gemini_m1_open_trl_20k_nectar_step_dpo
Text Generation
•
0.6B
•
Updated
•
8
vidyc/direct_dpo_gemini_m1_open_trl_20k_tulu_step_dpo
Text Generation
•
0.6B
•
Updated
•
6
vidyc/direct_dpo_gemini_m1_open_trl_20k_nectar_step_dpo
Text Generation
•
0.6B
•
Updated
•
5
vidyc/direct_dpo_gemini_m1_open_trl_20k_skywork_step_dpo
Text Generation
•
0.6B
•
Updated
•
5
vidyc/direct_dpo_trl_20k_gemini_m1_open_step_dpo_math_preference_dpo
Text Generation
•
0.6B
•
Updated
•
7
vidyc/direct_dpo_trl_20k_gemini_m1_open_step_dpo_2epoch
Text Generation
•
0.6B
•
Updated
•
7
vidyc/direct_dpo_trl_20k_gemini_m1_open_step_dpo
Text Generation
•
0.6B
•
Updated
•
7
vidyc/direct_dpo_trl_20k_gemini_m1_open
Text Generation
•
0.6B
•
Updated
•
7
vidyc/direct_dpo_trl_10k_gemini_m1_open
Text Generation
•
0.6B
•
Updated
•
6
vidyc/tulu_sft_dpo_gemini_m1_open_answer_bs2
Text Generation
•
0.6B
•
Updated
•
6
vidyc/direct_dpo_trl_20_kdpo_gemini_m1_open_answer
Text Generation
•
0.6B
•
Updated
•
7
vidyc/tulu_sft_dpo_gemini_m1_open_answer
Text Generation
•
0.6B
•
Updated
•
8
vidyc/direct_dpo_gemini_m1_open_answer
Text Generation
•
0.6B
•
Updated
•
7
vidyc/tulu_sft_dpo_tulu_skywork_lr_1e5_batch_size_6_2epoch
Text Generation
•
0.6B
•
Updated
•
7
vidyc/tulu_sft_dpo_tulu_skywork_lr_1e5_batch_size_6_1epoch
Text Generation
•
0.6B
•
Updated
•
5
vidyc/direct_dpo_tulu_skywork
Text Generation
•
0.6B
•
Updated
•
13
vidyc/tulu_sft_dpo_trl_20k_batch_size_10
Text Generation
•
0.6B
•
Updated
•
9
vidyc/tulu_sft_dpo_trl_20k
Text Generation
•
0.6B
•
Updated
•
7
vidyc/tulu_sft_dpo_tulu_skywork
Text Generation
•
0.6B
•
Updated
•
8
vidyc/base_model_tulu_sft
Text Generation
•
0.6B
•
Updated
•
8
vidyc/direct_dpo_tak_stak
Text Generation
•
0.6B
•
Updated
•
7
vidyc/direct_dpo_full_true_base
Text Generation
•
0.6B
•
Updated
•
7
vidyc/direct_dpo_dpo_mix_005_beta
Text Generation
•
0.6B
•
Updated
•
4
vidyc/direct_dpo_dpo_mix_1e4_lr
Text Generation
•
0.6B
•
Updated
•
8
Text Generation
•
0.6B
•
Updated
•
8