模型73°
TwIL-LM3-Pro在BIG-Bench Hard逻辑子集达95.4%
精选理由
TwIL-LM3-Pro小参数高性能，本地就能跑，适合开发者使用。
TwIL-LM3-Pro是一个仅36.6亿参数的开源模型。该模型在BIG-Bench Hard的逻辑子集测试中取得了95.4%的高分。这个小型模型可以在笔记本电脑上本地运行。通过专门的训练后优化，可以针对特定任务获得大量小型模型。
原文 · Ate-a-Pi
This open-source model scores 95.4% on BIG-Bench Hard’s logic subset with just 3.66B parameters.
TwIL-LM3-Pro is a model small enough to run locally on a laptop.
Specialized post-training is super cool. You can get a ton of small models when you focus on specific tasks. https://t.co/EwqiKKbr3t
