yale-nlp (Yale NLP Lab)

Collections 1

Model and data collection for our work "Understanding Reference Policies in Direct Preference Optimization" (https://arxiv.org/abs/2407.13709)

spaces 1

InstruSumEval

models 38

datasets 6

yale-nlp/DocMath-Eval

Preview • Updated 23 days ago • 62

yale-nlp/FinanceMath

Viewer • Updated Aug 10 • 1.2k • 23

yale-nlp/KnowledgeMath

Viewer • Updated Aug 10 • 1.2k • 6

yale-nlp/RefDPO

Viewer • Updated Jul 18 • 312k • 6

yale-nlp/FOLIO

Viewer • Updated Dec 21, 2023 • 1.2k • 594 • 17

yale-nlp/QTSumm

Viewer • Updated Nov 7, 2023 • 7.11k • 156 • 5

Yale NLP Lab

AI & ML interests

Collections 1

yale-nlp/RefDPO

yale-nlp/tulu2-7b-dpo-beta-0.1

yale-nlp/tulu2-7b-dpo-beta-0.02

yale-nlp/tulu2-7b-dpo-beta-0.005

spaces 1

InstruSumEval

models 38

yale-nlp/tulu2-7b-dpo-mistralv2-7b-beta-0.005

yale-nlp/tulu2-7b-dpo-beta-0.01

yale-nlp/tulu2-7b-dpo-beta-0.05

yale-nlp/mistral-likelihood

yale-nlp/mistral-probability

yale-nlp/tulu2-7b-dpo-beta-0.1

yale-nlp/mistral-7b-dpo-mistralv2-7b-beta-0.005

yale-nlp/mistral-7b-dpo-mistralv2-7b-beta-0.01

yale-nlp/mistral-7b-dpo-mistralv2-7b-beta-0.1

yale-nlp/mistral-7b-dpo-mistralv2-7b-beta-1.0

datasets 6

yale-nlp/DocMath-Eval

yale-nlp/FinanceMath

yale-nlp/KnowledgeMath

yale-nlp/RefDPO

yale-nlp/FOLIO

yale-nlp/QTSumm

AI & ML interests

Team members 8

Collections 1

spaces 1

InstruSumEval

models 38 Sort: Recently updated

datasets 6 Sort: Recently updated

models 38

datasets 6