# Vocabulary Trimmed [xlm-roberta-base](https://huggingface.co/xlm-roberta-base): `vocabtrimmer/xlm-roberta-base-trimmed-it-5000` 
This model is a trimmed version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) by [`vocabtrimmer`](https://github.com/asahi417/lm-vocab-trimmer), a tool for trimming vocabulary of language models to compress the model size.
Following table shows a summary of the trimming process.

|                            | xlm-roberta-base   | vocabtrimmer/xlm-roberta-base-trimmed-it-5000   |
|:---------------------------|:-------------------|:------------------------------------------------|
| parameter_size_full        | 278,295,186        | 89,890,186                                      |
| parameter_size_embedding   | 192,001,536        | 3,841,536                                       |
| vocab_size                 | 250,002            | 5,002                                           |
| compression_rate_full      | 100.0              | 32.3                                            |
| compression_rate_embedding | 100.0              | 2.0                                             |


Following table shows the parameter used to trim vocabulary.

 | language   | dataset                     | dataset_column   | dataset_name   | dataset_split   |   target_vocab_size |   min_frequency |
|:-----------|:----------------------------|:-----------------|:---------------|:----------------|--------------------:|----------------:|
| it         | vocabtrimmer/mc4_validation | text             | it             | validation      |                5000 |               2 |