Conditional Program stores LLM n-gram lookup tables at two bits
For DeepSeek, the method cuts table storage from 203GB to 51GB versus keeping full embeddings.
Stories per day · 30 days
2 RSS
2 stories, newest first · one card per story
Stories tagged #n-gram
FactorEngram: Factorized N-gram Memory with Basis-Level Gating for Language Models
FactorEngram adds factorized n-gram memory with basis-level gating to language models.