Shane Segal

shanes-cerebras's activity

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

upvoted a paper 9 days ago

Stabilizing Reinforcement Learning with LLMs: Formulation and Practices

Paper • 2512.01374 • Published 10 days ago • 85

upvoted a collection 21 days ago

Cerebras REAP

Collection

Sparse MoE models compressed using REAP (Router-weighted Expert Activation Pruning) method • 19 items • Updated 2 days ago • 52

upvoted a paper about 2 months ago

REAP the Experts: Why Pruning Prevails for One-Shot MoE compression

Paper • 2510.13999 • Published Oct 15 • 5

upvoted a paper 5 months ago

Dynamic Chunking for End-to-End Hierarchical Sequence Modeling

Paper • 2507.07955 • Published Jul 10 • 25

liked a model 6 months ago

mistralai/Magistral-Small-2506

24B • Updated Jul 28 • 14.6k • 606

liked a dataset 11 months ago

facebook/winoground

Viewer • Updated Oct 22, 2024 • 400 • 1.44k • 104