Maximum LLM capability per parameter, measured on five benchmarks, has grown exponentially, doubling about every three months.
Gqa: Training generalized multi-query transformer models from multi-head checkpoints
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Densing Law of LLMs
Maximum LLM capability per parameter, measured on five benchmarks, has grown exponentially, doubling about every three months.