PulseAugur
EN
LIVE 11:14:16
ENTITY Llama-300M

Llama-300M

PulseAugur coverage of Llama-300M — every cluster mentioning Llama-300M across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
0
1 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
0
1 over 90d
TIER MIX · 90D
TOPICS
RECENT · PAGE 1/1 · 1 TOTAL
  1. RESEARCH · CL_133189 ·

    GIFT method speeds up LLM pretraining with geometry-informed gradients · 2 sources tracked

    Researchers have developed GIFT, a novel method for optimizing large language model (LLM) pretraining by improving gradient communication. GIFT transforms gradients into a geometry-aware coordinate system before quantiz…