AI Grimoire
09 — siblings
serving/
tuning/
orchestration/

Tooling / tuning

Training and tuning

Fine-tuning is a solved problem in the sense that the algorithms are published and the memory arithmetic is understood. These are the libraries that spare you implementing it — mostly wrappers around the same handful of methods, differing in how much they assume and how much they optimise.

4 entries.

Entries

09.02.1
Config-Driven Fine-Tuningcommon
Axolotl, LLaMA-Factory and the case for a YAML file instead of a script.
09.02.2
PEFT and TRLstandard
The adapter library and the preference-training library, and how they compose.
09.02.3
Transformersstandard
The reference implementation of nearly every architecture, and the format everything reads.
09.02.4
Unslothcommon
Hand-written kernels and manual backward passes for fine-tuning on one GPU.