Supersonic Labs发布1.44亿参数本地分类模型Julia-1
SupersonicLabs/Julia-1 · Hugging Face
New open source Jev like model for running on local devices from a group called Supersonic Labs.
来自 Supersonic Labs 的一款类似 Jev 的新型开源模型，可在本地设备上运行。
It's a 144M param local non-generative local classifier.
它是一个拥有 144M 参数的本地非生成式分类器。
From their site:
根据其官网介绍：
Julia 1 opens our research into compact decision models. It builds on mmBERT-small, a multilingual encoder, and chooses among answers supplied with a question. It has 144.3 million parameters and runs on a CPU.
Julia 1 开启了我们对紧凑决策模型的研究。它基于 mmBERT-small（一种多语言编码器），并在与问题一同提供的答案中进行选择。该模型拥有 1.443 亿个参数，可在 CPU 上运行。
Our question: can one model classify, rank levels, and answer yes-or-no questions as the options change? Julia 1 is the first result of that investigation. Here are its successes, its failures, and the methods we used to measure them.
我们的问题是：一个模型能否在选项变化时进行分类、等级排序并回答是非题？Julia 1 是该项调查的首个成果。以下是它的成功之处、失败案例以及我们用于评估这些结果的方法。
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力