mrq 5479d2eacc more tweaks to the new implementation (properly trim the len stuff to save some params, decoder to d_ffn expansion to 2 to maybe also make it faster, etc.)		2025-03-18 19:34:37 -05:00
..
attention	wow that was fast	2025-03-04 23:17:18 -06:00
__init__.py	decoupled llama backend to avoid any funny changes from transformers, removed other backends since i dont think i'll ever bother using them	2025-02-27 19:00:37 -06:00
llama.py	more tweaks to the new implementation (properly trim the len stuff to save some params, decoder to d_ffn expansion to 2 to maybe also make it faster, etc.)	2025-03-18 19:34:37 -05:00