PrincetonPLI/Eagle-X2-Llama3-8B-VisualAnalogy-MixPlus-120k Image-Text-to-Text • Updated 13 days ago • 8
PrincetonPLI/Eagle-X2-Llama3-8B-VisualAnalogy-AlignMixPlus-120k Image-Text-to-Text • Updated 13 days ago • 12
PrincetonPLI/Eagle-X2-Llama3-8B-TableReadout-MixPlus-240k Image-Text-to-Text • Updated 13 days ago • 26
PrincetonPLI/Eagle-X2-Llama3-8B-TableReadout-AlignMixPlus-240k Image-Text-to-Text • Updated 13 days ago • 12
PrincetonPLI/Eagle-X2-Llama3-8B-GridNavigation-MixPlus-120k Image-Text-to-Text • Updated 13 days ago • 7
PrincetonPLI/Eagle-X2-Llama3-8B-GridNavigation-AlignMixPlus-120k Image-Text-to-Text • Updated 13 days ago • 7
PrincetonPLI/Eagle-X2-Llama3-8B-ConsecutiveTableReadout-Mix-160k Image-Text-to-Text • Updated 13 days ago • 7
VLM_S2H Collection Model checkpoints for "Generalizing from SIMPLE to HARD Visual Reasoning" • 9 items • Updated 13 days ago
MeCO Collection Models for Metadata Conditioning Accelerates Language Model Pre-training • 2 items • Updated 13 days ago