Tiny Reasoning Models
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
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. It outperforms or matches full fine-tuned models on reasoning tasks like AIME and MATH with only ~$9 post-training cost, demonstrating that efficient reasoning can be instilled via minimal updates to a tiny model.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack