scottgeng00/delta_learning_tulu3-sft-mix_model_ladder
Viewer • Updated • 515k • 875
Scott Geng
scottgeng00
AI & ML interests
None yet
Organizations
scottgeng00/delta_learning_num_sections_3section_tied
Viewer • Updated • 16.4k • 12
scottgeng00/delta_learning_num_sections
Viewer • Updated • 21.1k • 146
scottgeng00/delta_learning_ufweak
Viewer • Updated • 60.4k • 14
scottgeng00/secret_gpt_preferences_for_moo_moo
Viewer • Updated • 192k • 95
scottgeng00/olmo-3-preference-mix-deltas_reasoning-yolo_scottmix-DECON-qwen32b_sft
Viewer • Updated • 150k • 32
scottgeng00/olmo-3-preference-mix-deltas_reasoning-chosen_qwen4b-yolo_scottmix-DECON
Viewer • Updated • 294k • 114 • 1
scottgeng00/olmo-3-preference-mix-deltas_reasoning-yolo_scottmix-DECON-chfiltered
Viewer • Updated • 279k • 27
scottgeng00/olmo-3-preference-mix-deltas_reasoning-chosen_qwen8b-yolo_scottmix-DECON
Viewer • Updated • 268k • 76
scottgeng00/olmo-3-preference-mix-deltas_reasoning-chosen_qwen8b-yolo_victoria_hates_code-DECON
Viewer • Updated • 276k • 50
scottgeng00/olmo-3-preference-mix-deltas_reasoning-chosen_qwen8b-chat35-DECON
Viewer • Updated • 221k • 154
scottgeng00/olmo-3-preference-mix-deltas_reasoning-chosen_qwen8b-yolo_even_split-DECON
Viewer • Updated • 498k • 57
scottgeng00/rlvr-prompts_responses-mixin_it_up-v2
Viewer • Updated • 131k • 14
scottgeng00/rlvr-prompts-mixin_it_up-v2
Viewer • Updated • 200k • 5
scottgeng00/rlvr_mixin_it_up-all_delta_no_vr-v2
Viewer • Updated • 94.2k • 17
scottgeng00/rlvr_mixin_it_up-deltas-verified_qwen32b_math-verified_qwen32b_general-v2
Viewer • Updated • 42.1k • 6
scottgeng00/rlvr_mixin_it_up-deltas-verified_qwen06b_math-verified_qwen06b_general-v2
Viewer • Updated • 53.3k • 13
scottgeng00/rlvr_mixin_it_up-deltas-verified_qwen32b_06b_math-verified_qwen32b_06b_general-v2
Viewer • Updated • 58.8k • 5
scottgeng00/rlvr_mixin_it_up-deltas-verified_qwen06b_math-verified_qwen32b_06b_general-v2
Viewer • Updated • 54k • 18
scottgeng00/rlvr_mixin_it_up-deltas-verified_qwen06b_math-qwen32b_06b_general-v2
Viewer • Updated • 73.1k • 31
scottgeng00/rlvr_mixin_it_up-deltas-verified_qwen32b_06b_math-qwen32b_06b_general-v2
Viewer • Updated • 77.9k • 24
scottgeng00/olmo-3-preference-mix-deltas-gpt_and_100k_base_complement-DECON
Viewer • Updated • 1.77M • 728
scottgeng00/olmo-3-preference-mix-deltas-complement2-yolo_downsample_wildchat_to_multilingual-DECON
Viewer • Updated • 1.16M • 58
scottgeng00/olmo-3-preference-mix-deltas-complement2-yolo1-DECON
Viewer • Updated • 427k • 14
scottgeng00/olmo-3-preference-mix-deltas-complement2-yolo_og_no_multilingual-DECON
Viewer • Updated • 1.12M • 22
scottgeng00/olmo-3-preference-mix-deltas-complement2-yolo_even_split_no_multilingual-DECON
Viewer • Updated • 332k • 30
scottgeng00/olmo-3-preference-mix-deltas-complement2-yolo_even_split-DECON
Viewer • Updated • 373k • 88
scottgeng00/olmo-3-preference-mix-deltas-complement2-yolo_victoria_only_speaks_english-DECON
Viewer • Updated • 381k • 63
scottgeng00/olmo-3-preference-mix-deltas-complement2-yolo_victoria_hates_code-DECON
Viewer • Updated • 234k • 18
scottgeng00/olmo-3-preference-mix-deltas-complement2-yolo_scottmix-DECON
Viewer • Updated • 260k • 15