Cites: Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference

4 citation edges inside this catalog. A title match is weaker evidence than an identifier match. Zero entries does not mean no citations on the web.

• GLU Variants Improve Transformer
  arxiv:2002.05202 · evidence: id
• Cramming: Training a Language Model on a Single GPU in One Day
  arxiv:2212.14034 · evidence: title
• Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations
  arxiv:2405.18392 · evidence: id
• The Llama 3 Herd of Models
  arxiv:2407.21783 · evidence: id