- 谁
- Hugging Face
- 引文
In the rest of the post we will refer to the models as "decision models" instead of "system one models".
发生了什么
Hugging Face 介绍了决策模型：这类模型接收一个状态和类型化问题，并返回带有概率的决策，而不是生成文本。文章将选择、评分和是/否这几种基本类型与传统分类和零样本分类进行了区分，随后演示了 Transformers 和 llama.cpp 中的支持、如何在 Hub 上发现模型，以及一个微调示例。文章还指出，TRL 的支持仍处于开放拉取请求阶段。
推荐理由
文章将决策模型与传统分类器和零样本分类器进行比较，随后展示了其类型化输出如何适配用于推理、服务和训练的共享接口。
接下来读什么
查看这件事的完整进展Hugging Face Explains Decision Models and Their Ecosystem Support这件事到目前为止
Hugging Face explained decision models as systems that take a state and typed questions and return decisions with probabilities instead of generating text. The post describes choice, score, and yes-or-no outputs, and shows support in Transformers and llama.cpp, model discovery on the Hub, and an example of fine-tuning. Hugging Face distinguishes decision models from conventional and zero-shot classification. Support in TRL was still an open pull request when the post was written.