← all tags

#fine-tuning

3 posts tagged fine-tuning.

Thoughts

Fine-tuning tutorials just turned model training into paint-by-numbers

Step-by-step fine-tuning guides are creating a generation of practitioners who can follow recipes but can't cook.

fine-tuning qlora model-training tutorials

Parameter efficiency is just premature optimisation disguised as innovation

The obsession with minimal parameters is solving yesterday's problems whilst creating tomorrow's technical debt.

parameter-efficiency fine-tuning model-compression optimisation

Tools & Experiments

Sakana AI's Doc-to-LoRA and Text-to-LoRA

Hypernetworks that instantly convert documents or natural language instructions into LoRA adapters without training.

experimental
lora hypernetworks zero-shot adaptation fine-tuning