Collection by
28 days ago
28 days ago
Collections
Discover the best community collections!
Collections including paper arxiv:2412.09764
Collection by
28 days ago
28 days ago
Collection by
28 days ago
28 days ago
Collection by
28 days ago
28 days ago
Collection by
28 days ago
28 days ago
Collection by
28 days ago
28 days ago
Collection by
28 days ago
28 days ago
Collection by
8 days ago
8 days ago
-
STaR: Bootstrapping Reasoning With Reasoning
Paper • 2203.14465 • Published • 8 -
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
Paper • 2401.06066 • Published • 47 -
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
Paper • 2405.04434 • Published • 17 -
Prompt Cache: Modular Attention Reuse for Low-Latency Inference
Paper • 2311.04934 • Published • 29
Collection by
28 days ago
28 days ago
-
MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs
Paper • 2402.15627 • Published • 35 -
One Wide Feedforward is All You Need
Paper • 2309.01826 • Published • 32 -
Fast Feedforward Networks
Paper • 2308.14711 • Published • 3 -
Memory Layers at Scale
Paper • 2412.09764 • Published • 3
Collection by
28 days ago
28 days ago
-
Prompt-to-Prompt Image Editing with Cross Attention Control
Paper • 2208.01626 • Published • 2 -
BERT Rediscovers the Classical NLP Pipeline
Paper • 1905.05950 • Published • 2 -
A Multiscale Visualization of Attention in the Transformer Model
Paper • 1906.05714 • Published • 2 -
Analyzing Transformers in Embedding Space
Paper • 2209.02535 • Published • 3