·
AI & ML interests
NLP, Synthetic Data
Organizations
dmayhem93/agieval-sat-math
Viewer
• Updated • 220 • 2.12k
• 13
dmayhem93/agieval-sat-en-without-passage
Viewer
• Updated • 206 • 367
Viewer
• Updated • 206 • 2.03k
• 3
dmayhem93/agieval-logiqa-zh
Viewer
• Updated • 651 • 203
dmayhem93/agieval-logiqa-en
Viewer
• Updated • 651 • 2.51k
dmayhem93/agieval-lsat-rc
Viewer
• Updated • 269 • 600
dmayhem93/agieval-lsat-lr
Viewer
• Updated • 510 • 2.17k
• 1
dmayhem93/agieval-lsat-ar
Viewer
• Updated • 230 • 2.22k
• 5
dmayhem93/agieval-gaokao-physics
Viewer
• Updated • 200 • 2.29k
• 1
dmayhem93/agieval-gaokao-mathqa
Viewer
• Updated • 351 • 2.16k
• 1
dmayhem93/agieval-gaokao-history
Viewer
• Updated • 235 • 377
• 1
dmayhem93/agieval-gaokao-geography
Viewer
• Updated • 199 • 374
• 1
dmayhem93/agieval-gaokao-english
Viewer
• Updated • 306 • 313
• 1
dmayhem93/agieval-gaokao-chinese
Viewer
• Updated • 246 • 316
• 2
dmayhem93/agieval-gaokao-chemistry
Viewer
• Updated • 207 • 2.54k
• 1
dmayhem93/agieval-gaokao-biology
Viewer
• Updated • 210 • 2.31k
• 2
dmayhem93/agieval-aqua-rat
Viewer
• Updated • 254 • 603
• 3
dmayhem93/self-critiquing-base-selected-900-prompt-continuation
Viewer
• Updated • 900 • 13
• 1
dmayhem93/self-critiquing-base-selected-900
Viewer
• Updated • 900 • 18
dmayhem93/self-critiquing-base-topic-embeddings
Viewer
• Updated • 2.76k • 5
dmayhem93/self-critiquing-refine-continuations
Viewer
• Updated • 5.12k • 14
dmayhem93/self-critiquing-critique-continuations
Viewer
• Updated • 9.44k • 33
dmayhem93/self-critiquing-base-test-continuations
Viewer
• Updated • 10.6k • 14
Viewer
• Updated • 1.05M • 120
• 5
dmayhem93/self-critiquing-helpful-sft
Viewer
• Updated • 13.9k • 16
dmayhem93/self-critiquing-base
Viewer
• Updated • 57.7k • 15
• 2
dmayhem93/self-critiquing-critique-and-refine
Viewer
• Updated • 39.2k • 29
• 2
dmayhem93/self-critiquing-refine
Viewer
• Updated • 39.2k • 15
• 1
dmayhem93/self-critiquing-critique
Viewer
• Updated • 70.9k • 10
• 1
dmayhem93/self-critiquing-critique-answer-ranking
Viewer
• Updated • 11k • 35