4 commits

Author	SHA1	Message	Date
Roland Tannous	58753151ef	change train_on_completions to true	2026-02-19 06:02:16 +00:00
Roland Tannous	028408e432	chore: override model defaults to use max_steps=30, save_steps=30, num_epochs=0 for testing	2026-02-17 18:46:23 +00:00
sshah229	9b5e02029e	added inference defaults from unsloth guides	2026-02-15 02:13:24 -07:00
Roland Tannous	0ec1139f92	added model yaml config files	2026-02-02 18:22:14 +00:00