Xingyu Zhu

JupiterZhu's activity

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

published 6 models 10 days ago

JupiterZhu/T2MLR_Baseline_997M_50B_FineWebEdu

Text Generation • 1.0B • Updated 10 days ago • 666

JupiterZhu/T2MLR_Baseline_368M_50B_FineWebEdu

Text Generation • 0.4B • Updated 10 days ago • 670

JupiterZhu/T2MLR_Baseline_136M_50B_FineWebEdu

Text Generation • 0.1B • Updated 10 days ago • 658

JupiterZhu/T2MLR_Baseline_997M_10B_FineWebEdu

Text Generation • 1.0B • Updated 10 days ago • 657

JupiterZhu/T2MLR_Baseline_368M_10B_FineWebEdu

Text Generation • 0.4B • Updated 10 days ago • 625

JupiterZhu/T2MLR_Baseline_136M_10B_FineWebEdu

Text Generation • 0.1B • Updated 10 days ago • 610

updated a collection 10 days ago

T2MLR

Collection

T2MLR pretraining checkpoints: 3 scales x 2 token budgets, trained from scratch on FineWeb-Edu. • 13 items • Updated 10 days ago

updated a model 10 days ago

JupiterZhu/T2MLR_Baseline_997M_50B_FineWebEdu

Text Generation • 1.0B • Updated 10 days ago • 666

updated a collection 10 days ago

T2MLR

Collection

T2MLR pretraining checkpoints: 3 scales x 2 token budgets, trained from scratch on FineWeb-Edu. • 13 items • Updated 10 days ago

updated a model 10 days ago

JupiterZhu/T2MLR_Baseline_368M_50B_FineWebEdu

Text Generation • 0.4B • Updated 10 days ago • 670

updated a collection 10 days ago

T2MLR

Collection

T2MLR pretraining checkpoints: 3 scales x 2 token budgets, trained from scratch on FineWeb-Edu. • 13 items • Updated 10 days ago

updated a model 10 days ago

JupiterZhu/T2MLR_Baseline_136M_50B_FineWebEdu

Text Generation • 0.1B • Updated 10 days ago • 658

updated a collection 10 days ago

T2MLR

Collection

T2MLR pretraining checkpoints: 3 scales x 2 token budgets, trained from scratch on FineWeb-Edu. • 13 items • Updated 10 days ago

updated a model 10 days ago

JupiterZhu/T2MLR_Baseline_997M_10B_FineWebEdu

Text Generation • 1.0B • Updated 10 days ago • 657

updated a collection 10 days ago

T2MLR

Collection

T2MLR pretraining checkpoints: 3 scales x 2 token budgets, trained from scratch on FineWeb-Edu. • 13 items • Updated 10 days ago

updated a model 10 days ago

JupiterZhu/T2MLR_Baseline_368M_10B_FineWebEdu

Text Generation • 0.4B • Updated 10 days ago • 625

updated a collection 10 days ago

T2MLR

Collection

T2MLR pretraining checkpoints: 3 scales x 2 token budgets, trained from scratch on FineWeb-Edu. • 13 items • Updated 10 days ago

updated a model 10 days ago

JupiterZhu/T2MLR_Baseline_136M_10B_FineWebEdu

Text Generation • 0.1B • Updated 10 days ago • 610

upvoted a paper about 1 month ago

Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression

Paper • 2609.36322 • Published Sep 28 • 37

submitted a paper to Daily Papers about 1 month ago

Periodic Weak Spots: Phase Sensitivity from Chunked KV-Cache Compression

Paper • 2609.36322 • Published Sep 28 • 37