Inheritance-intensity is a small multilingual encoder model based on ModernBert to rate the intensity of the thematic of inheritance in any given text.

Inheritance-thematic has been trained on cultural heritage texts in English, French, German and Italian for the Philherit project. The main use of the model is to filter for text with a higher chance of relevancy for the project's scope.

Labels

The model returns the following labels:

  • Non-existent: no actual allusion to inheritance.
  • In passing: very short mention, but far off from being a major topic of the text.
  • A topic: one of the key topics of the text, but not the only one.
  • Main topic: the topic of inheritance completely dominates the text, to the exclusion of all other topics.

Depending on the size of original cultural heritage corpus, it's possible to keep texts either classified as topic/main topic, or sometimes only main topic.

Downloads last month
2
Safetensors
Model size
396M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Pclanglais/Inheritance-Intensity

Finetuned
(725)
this model