Collection of datasets and models for our paper "Whose Boat Does it Float? Improving Personalization in Preference Tuning via Inferred User Personas"
Nishant Balepur
nbalepur
AI & ML interests
NLP
Organizations
models
8
nbalepur/Llama-3.1-8B-PT-DPO-HHH
Updated
nbalepur/Llama-3.1-8B-PT-DPO-Mnemonic
Updated
nbalepur/Llama-3.1-8B-PT-DPO-BeaverTails
Text Generation
•
8B
•
Updated
•
4
nbalepur/Llama-3.1-8B_copy_persona_False_Mnemonic_dpo_chosen
Text Generation
•
8B
•
Updated
•
2
nbalepur/Llama-3.1-8B_copy_persona_False_Safe_RLHF_dpo_chosen
Text Generation
•
8B
•
Updated
•
3
nbalepur/LLama-2-70b-Mnemonic-Tokenizer
Updated
nbalepur/LLama-2-70b-Mnemonic-SFT
Text Generation
•
69B
•
Updated
•
8
•
1
nbalepur/LLama-2-70b-Mnemonic-DPO
Text Generation
•
69B
•
Updated
•
4
datasets
100
nbalepur/deep-research-actions
Viewer
•
Updated
•
21.4k
•
145
nbalepur/mcqa-bench-base
Viewer
•
Updated
•
12.3k
•
15
nbalepur/cheating-reasoners-mcqa-large
Viewer
•
Updated
•
7.44k
•
13
nbalepur/google-query-wellformedness
Viewer
•
Updated
•
25.1k
•
4
nbalepur/cheating-reasoners
Viewer
•
Updated
•
9.39k
•
21
nbalepur/Planorama-user-data
Viewer
•
Updated
•
300
•
11
nbalepur/planorama_without_label_swap_fixed2
Viewer
•
Updated
•
300
•
6
nbalepur/planorama_irt_swap_newslope
Viewer
•
Updated
•
300
•
6
nbalepur/planorama_without_label_swap_fixed
Viewer
•
Updated
•
300
•
7
nbalepur/planorama_irt_swap2
Viewer
•
Updated
•
300
•
4