Tobi Lutke f96766cce8 Fix GRPO model loading to use SFT base first 4 mēneši atpakaļ
..
.gitignore f6a6716c44 Refactor evals into separate run and score scripts 4 mēneši atpakaļ
queries.txt f6a6716c44 Refactor evals into separate run and score scripts 4 mēneši atpakaļ
run.py f96766cce8 Fix GRPO model loading to use SFT base first 4 mēneši atpakaļ
score.py f6a6716c44 Refactor evals into separate run and score scripts 4 mēneši atpakaļ