ZHONGZHU ZHOU

Zhongzhu's activity

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

upvoted a paper 12 days ago

Massive Activations in Hybrid Linear Attention Large Language Models: Pre-Attention Spikes and Inter-Spike Plateaus

Paper • 2608.12149 • Published 14 days ago • 30

updated a model 14 days ago

Zhongzhu/OSCAR-RotationZoo

Text Generation • Updated 14 days ago • 8

updated a model about 1 month ago

Zhongzhu/Inkling-GDN-Linearized

954B • Updated Jul 23 • 15

published a model about 1 month ago

Zhongzhu/Inkling-GDN-Linearized

954B • Updated Jul 23 • 15

commented 2 papers 2 months ago

Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation

Paper • 2606.16429 • Published Jun 15 • 5 •

5

Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation

Paper • 2606.16429 • Published Jun 15 • 5 •

5

upvoted a paper 2 months ago

Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation

Paper • 2606.16429 • Published Jun 15 • 5

submitted a paper to Daily Papers 2 months ago

Taylor-Calibrate: Principled Initialization for Hybrid Linear Attention Distillation

Paper • 2606.16429 • Published Jun 15 • 5

updated 4 models 3 months ago

Zhongzhu/OSCAR-LLAMACPP-Qwen3-32B-INT2-KV

Text Generation • 33B • Updated Jun 8 • 19

Zhongzhu/OSCAR-LLAMACPP-Qwen3-4B-Thinking-2507-INT2-KV

Text Generation • 4B • Updated Jun 8 • 8

Zhongzhu/OSCAR-RotationZoo

Text Generation • Updated 14 days ago • 8

Zhongzhu/OSCAR-LLAMACPP-Qwen3-32B-INT2-KV

Text Generation • 33B • Updated Jun 8 • 19

published a model 3 months ago

Zhongzhu/OSCAR-LLAMACPP-Qwen3-32B-INT2-KV

Text Generation • 33B • Updated Jun 8 • 19

updated a model 3 months ago

Zhongzhu/OSCAR-LLAMACPP-Gemma-4-12B-it-INT2-KV

12B • Updated Jun 7 • 22

published a model 3 months ago

Zhongzhu/OSCAR-LLAMACPP-Gemma-4-12B-it-INT2-KV

12B • Updated Jun 7 • 22

updated a model 3 months ago

Zhongzhu/OSCAR-LLAMACPP-Qwen3-4B-Thinking-2507-INT2-KV

Text Generation • 4B • Updated Jun 8 • 8

published a model 3 months ago

Zhongzhu/OSCAR-LLAMACPP-Qwen3-4B-Thinking-2507-INT2-KV

Text Generation • 4B • Updated Jun 8 • 8

New activity in Zhongzhu/OSCAR-RotationZoo 3 months ago

Improve model card metadata and documentation

1

#1 opened 3 months ago by

nielsr

liked a model 3 months ago

Zhongzhu/OSCAR-RotationZoo

Text Generation • Updated 14 days ago • 8

submitted a paper to Daily Papers 3 months ago

OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization

Paper • 2605.17757 • Published May 18 • 66