TinyGauss 1.1B

Adding math capabilities to models in the 1B parameter count regime, with the main objective of providing Math and logic reasoning capabilities to LLMs meant for robotics.

MathInstruct Finetune over TinyLlama/TinyLlama-1.1B-Chat-v1.0. The model is capable of following corrections from the user when it makes mistakes; opening the door to models that can correct mistakes following user feedback in a multi-turn interaction.

Finetuned using LLaMAFactory.