Xingyu Zhu

JupiterZhu's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a collection 7 days ago

T2MLR

Collection

T2MLR pretraining checkpoints: 3 scales x 2 token budgets, trained from scratch on FineWeb-Edu. • 7 items • Updated 7 days ago

published 6 models about 1 month ago

JupiterZhu/T2MLR_982M_lstart9_lend24_50B_FineWebEdu

Text Generation • 1B • Updated Aug 21 • 69

JupiterZhu/T2MLR_982M_lstart9_lend24_10B_FineWebEdu

Text Generation • 1B • Updated Aug 21 • 68

JupiterZhu/T2MLR_362M_lstart9_lend24_50B_FineWebEdu

Text Generation • 0.4B • Updated Aug 21 • 68

JupiterZhu/T2MLR_362M_lstart9_lend24_10B_FineWebEdu

Text Generation • 0.4B • Updated Aug 21 • 74

JupiterZhu/T2MLR_135M_lstart13_lend18_50B_FineWebEdu

Text Generation • 0.2B • Updated Aug 21 • 71

JupiterZhu/T2MLR_135M_lstart13_lend18_10B_FineWebEdu

Text Generation • 0.2B • Updated Aug 21 • 67

updated a collection about 1 month ago

T2MLR

Collection

T2MLR pretraining checkpoints: 3 scales x 2 token budgets, trained from scratch on FineWeb-Edu. • 7 items • Updated 7 days ago

updated 6 models about 1 month ago

JupiterZhu/T2MLR_982M_lstart9_lend24_50B_FineWebEdu

Text Generation • 1B • Updated Aug 21 • 69

JupiterZhu/T2MLR_982M_lstart9_lend24_10B_FineWebEdu

Text Generation • 1B • Updated Aug 21 • 68

JupiterZhu/T2MLR_362M_lstart9_lend24_50B_FineWebEdu

Text Generation • 0.4B • Updated Aug 21 • 68

JupiterZhu/T2MLR_362M_lstart9_lend24_10B_FineWebEdu

Text Generation • 0.4B • Updated Aug 21 • 74

JupiterZhu/T2MLR_135M_lstart13_lend18_50B_FineWebEdu

Text Generation • 0.2B • Updated Aug 21 • 71

JupiterZhu/T2MLR_135M_lstart13_lend18_10B_FineWebEdu

Text Generation • 0.2B • Updated Aug 21 • 67

upvoted a paper 4 months ago

Contextual Drag: How Errors in the Context Affect LLM Reasoning

Paper • 2602.04288 • Published Feb 4 • 2