arxiv:2411.15124
Victoria Graf
VGraf
AI & ML interests
None yet
Recent Activity
updated
a model
less than a minute ago
VGraf/4t_0.5p_safe_synth_mt_dpo_mix
updated
a model
less than a minute ago
VGraf/3t_0.5p_safe_synth_mt_dpo_mix
updated
a model
1 minute ago
VGraf/8t_0.3p_safe_synth_mt_dpo_mix
Organizations
Papers
1
models
12
VGraf/4t_0.5p_safe_synth_mt_dpo_mix
Feature Extraction
•
Updated
VGraf/3t_0.5p_safe_synth_mt_dpo_mix
Feature Extraction
•
Updated
VGraf/8t_0.3p_safe_synth_mt_dpo_mix
Feature Extraction
•
Updated
VGraf/8t_0.4p_safe_synth_mt_dpo_mix
Feature Extraction
•
Updated
VGraf/safe_stack_mt_dpo_mix
Feature Extraction
•
Updated
VGraf/safe_synth_mt_dpo_mix
Feature Extraction
•
Updated
VGraf/8t_0.7p_safe_synth_mt_dpo_mix
Feature Extraction
•
Updated
VGraf/8t_0.6p_safe_synth_mt_dpo_mix
Feature Extraction
•
Updated
VGraf/8t_0.5p_safe_synth_mt_dpo_mix
Feature Extraction
•
Updated
VGraf/7t_0.5p_safe_synth_mt_dpo_mix
Feature Extraction
•
Updated
datasets
74
VGraf/no_benign_pref_stack_0.2p_8t_dev
Viewer
•
Updated
•
6.85k
VGraf/safe_responses_no_benign_dev
Viewer
•
Updated
•
25.7k
VGraf/no_benign_tulu_pref
Viewer
•
Updated
•
6.85k
VGraf/safe_responses_dev_8maxturns_0.7prob
Viewer
•
Updated
•
75.7k
•
32
VGraf/safe_responses_dev_8maxturns_0.6prob
Viewer
•
Updated
•
65k
•
29
VGraf/safe_responses_dev_8maxturns_0.3prob
Viewer
•
Updated
•
32.6k
•
32
VGraf/safe_responses_dev_8maxturns_0.4prob
Viewer
•
Updated
•
43.7k
•
29
VGraf/safe_responses_dev_3maxturns_0.5prob
Viewer
•
Updated
•
20.3k
•
28
VGraf/safe_responses_dev_4maxturns_0.5prob
Viewer
•
Updated
•
27.1k
•
31
VGraf/safe_responses_dev_5maxturns_0.5prob
Viewer
•
Updated
•
34.3k
•
23