ToastyPigeon/Gemma-3-Confetti-12B
310
This is the same datamix as Glitter, but trained on the base model (gemma-3-12b-pt) instead of instruct. Gemma 3 instruct format was used for the instruct portions.
This is the same datamix as Glitter, but trained on the base model (gemma-3-12b-pt) instead of instruct. Gemma 3 instruct format was used for the instruct portions.