Distillation Experiments
Experiments comparing Distillation to Finetuning
September 1, 2024 · 2 min read
Experiments comparing Distillation to Finetuning
Distilling Large Language models in Small Language Models!
Tuning LLMs by only learning a fraction of weight updates!
Optimizing to improve legibility of an LLMs output!
Route between LLMs to optimize cost and quality!
The quality of a reranked retreiver and the speed of a bi-encoder retreiver!