10. Tiny Reasoning Models Tina is a family of 1.5B parameter reasoning models trained using LoRA-based reinforcement learning (RL) to achieve high reasoning accuracy at very low cost.
Tiny Reasoning Models: 1.5B Parameter Tina Family
By
–
By
–
10. Tiny Reasoning Models Tina is a family of 1.5B parameter reasoning models trained using LoRA-based reinforcement learning (RL) to achieve high reasoning accuracy at very low cost.