webAI发布TwIL-LM:1.7B和3B形式逻辑模型,本地硬件自动形式化

webAI Releases TwIL-LM: A 1.7B and 3B Formal-Logic Model Family for Autoformalization on Local Hardware

精选理由

想本地跑形式逻辑?TwIL-LM 1.7B和3B能翻译英文到一阶逻辑,3B只要4GB显存,但注意基准分数是未发布版本的。

AI 摘要

webAI发布了TwIL-LM模型家族,包含1.7B和3B参数版本,能将英文翻译成一阶逻辑并检查结论是否从前提推出。3B模型可在CPU或4GB显存上运行,1.7B模型下载大小为1.06GB。两个版本均采用非商业许可。模型卡显示,头条基准分数属于未发布的检查点,而非Hub上的权重。

图片来源 · marktechpost
原文 · marktechpost

webAI Releases TwIL-LM: A 1.7B and 3B Formal-Logic Model Family for Autoformalization on Local Hardware

webAI has released TwIL-LM, a family of formal-logic models at 1.7B and 3B parameters that translate English into first-order logic and check whether conclusions follow from premises. The 3B runs on CPU or 4GB of VRAM; the 1.7B downloads at 1.06GB. Both ship under a non-commercial license. The model card also shows that the headline benchmark scores belong to an unreleased checkpoint, not the weights on the Hub. The post webAI Releases TwIL-LM: A 1.7B and 3B Formal-Logic Model Family for Autoformalization on Local Hardware appeared first on MarkTechPost .