Pub Collection by EricAntoie Apr 6 - Training LLMs over Neurally Compressed Text Paper • 2404.03626 • Published Apr 4 • 21
llm efficiency Collection by mylonasc Apr 5 - Training LLMs over Neurally Compressed Text Paper • 2404.03626 • Published Apr 4 • 21
Papers - Inference - Multi-Model Collection by matlok Apr 5 - Training LLMs over Neurally Compressed Text Paper • 2404.03626 • Published Apr 4 • 21
Papers - Tokenizer - Neural Compression Collection by matlok Apr 5 - Training LLMs over Neurally Compressed Text Paper • 2404.03626 • Published Apr 4 • 21
Papers - Coding - Compression Collection by matlok Apr 5 - Training LLMs over Neurally Compressed Text Paper • 2404.03626 • Published Apr 4 • 21
Papers - Encoders - Compression Emergence with scale is unlikely Given the recent findings of [55], we anticipate that continuing to scale models beyond 2 billion parameters is unlik Collection by matlok Apr 5 - Training LLMs over Neurally Compressed Text Paper • 2404.03626 • Published Apr 4 • 21
Papers - Coding - Encoders Collection by matlok Apr 5 - Training LLMs over Neurally Compressed Text Paper • 2404.03626 • Published Apr 4 • 21
Papers - Training Research - Compression and Multi-Model Inf Collection by matlok Apr 5 - Training LLMs over Neurally Compressed Text Paper • 2404.03626 • Published Apr 4 • 21
Papers - Anthropic Collection by matlok May 4 - Training LLMs over Neurally Compressed Text Paper • 2404.03626 • Published Apr 4 • 21 In-context Learning and Induction Heads Paper • 2209.11895 • Published Sep 24, 2022 • 2
Papers - Coding - Distributed - Adaptive Computation Time Collection by matlok Apr 5 - Training LLMs over Neurally Compressed Text Paper • 2404.03626 • Published Apr 4 • 21