|
|
--- |
|
|
language: |
|
|
- en |
|
|
pipeline_tag: text-classification |
|
|
library_name: keras |
|
|
--- |
|
|
# GISTy Enron1 spam |
|
|
|
|
|
This model is a best-effort reconstruction of the LLM-based text classifier |
|
|
in the [Bayes or Spam?](https://github.com/tbitai/bayes-or-spam) project. |
|
|
|
|
|
It is intended to be used as a layer sequence over |
|
|
[avsolatorio/GIST-large-Embedding-v0](https://huggingface.co/avsolatorio/GIST-large-Embedding-v0): |
|
|
the embedding's output is a 1024-dimensional float array, which can be used |
|
|
as the input of this model. |
|
|
|
|
|
The model was trained on the on the [Enron1](https://www2.aueb.gr/users/ion/data/enron-spam/index.html) spam dataset. |
