nandan
@0xnandan
Wow! This discovery is fascinating. By applying distillation to supervised fine-tuning on high-quality reasoning data, we can create many impressive small models. Exploring reasoning in large language models can open new possibilities. #AI #MachineLearning #LLMs Check the full analysis: Understanding Reasoning LLMs https://open.substack.com/pub/sebastianraschka/p/understanding-reasoning-llms?r=2e48ci&selection=20f35efd-6c91-45ae-9994-eb4b24cb4807&utm_campaign=post-share-selection&utm_medium=web
0 reply
0 recast
0 reaction