Victoria Graf's picture

1

Victoria Graf

VGraf

·

AI & ML interests

None yet

Recent Activity

updated a dataset 7 days ago

VGraf/repeat_response_flip_tulu_5maxturns_big_truncated2048_gpt-4ochosen_gpt-3.5-turbo-0125rejected

published a dataset 7 days ago

VGraf/repeat_response_flip_tulu_5maxturns_big_truncated2048_gpt-4ochosen_gpt-3.5-turbo-0125rejected

updated a dataset 7 days ago

VGraf/paraphrase_train_dev_8maxturns_truncated2048_gpt-4ochosen_gpt-3.5-turbo-0125rejected

View all activity

Organizations

Papers 1

arxiv:2411.15124

models 15

VGraf/mt_dpo

Feature Extraction • 8B • Updated Mar 16 • 7

VGraf/no_benign_synth_mt_dpo_mix

Feature Extraction • 8B • Updated Mar 14 • 1

VGraf/no_benign_stack_mt_dpo_mix

Feature Extraction • 8B • Updated Mar 14 • 2

VGraf/8t_0.7p_safe_synth_mt_dpo_mix

Feature Extraction • 8B • Updated Mar 14

VGraf/8t_0.6p_safe_synth_mt_dpo_mix

Feature Extraction • 8B • Updated Mar 14

VGraf/8t_0.5p_safe_synth_mt_dpo_mix

Feature Extraction • 8B • Updated Mar 14

VGraf/7t_0.5p_safe_synth_mt_dpo_mix

Feature Extraction • 8B • Updated Mar 14 • 4

VGraf/6t_0.5p_safe_synth_mt_dpo_mix

Feature Extraction • 8B • Updated Mar 14 • 3

VGraf/5t_0.5p_safe_synth_mt_dpo_mix

Feature Extraction • 8B • Updated Mar 14 • 1

VGraf/4t_0.5p_safe_synth_mt_dpo_mix

Feature Extraction • 8B • Updated Mar 14

datasets 529

VGraf/repeat_response_flip_tulu_5maxturns_big_truncated2048_gpt-4ochosen_gpt-3.5-turbo-0125rejected

Viewer • Updated 7 days ago • 21.5k • 13

VGraf/paraphrase_train_dev_8maxturns_truncated2048_gpt-4ochosen_gpt-3.5-turbo-0125rejected

Viewer • Updated 7 days ago • 5.28k • 19

VGraf/general_responses_dev_8maxturns_truncated2048_gpt-4ochosen_gpt-3.5-turbo-0125rejected

Viewer • Updated 7 days ago • 5.19k • 21

VGraf/self-talk_gpt3.5_gpt4o_prefpairs_truncated2048_Qwen__Qwen3-32Bchosen_Qwen__Qwen3-0.6Brejected

Viewer • Updated 7 days ago • 10k • 23

VGraf/repeat_tulu_5maxturns_big_truncated2048_Qwen__Qwen3-32Bchosen_Qwen__Qwen3-0.6Brejected

Viewer • Updated 7 days ago • 4k • 21

VGraf/paraphrase_train_dev_8maxturns_truncated2048_Qwen__Qwen3-32Bchosen_Qwen__Qwen3-0.6Brejected

Viewer • Updated 7 days ago • 4k • 21

VGraf/general_responses_dev_8maxturns_truncated2048_Qwen__Qwen3-32Bchosen_Qwen__Qwen3-0.6Brejected

Viewer • Updated 7 days ago • 4k • 27

VGraf/multiturn-dpo-synthetic-context

Viewer • Updated 14 days ago • 44k • 31

VGraf/olmo-3-preference-mix-deltas_reasoning-yolo_scottmix-chosen_qwen32b_rejected_qwen4b-DECON

Viewer • Updated Sep 25 • 294k • 108

VGraf/olmo-3-preference-mix-deltas_reasoning-yolo_scottmix-chosen_qwen32b_rejected_qwen8b-DECON

Viewer • Updated Sep 25 • 165k • 9

View 529 datasets