# Vocabulary Trimmed [cardiffnlp/xlm-roberta-base-tweet-sentiment-en](https://huggingface.co/cardiffnlp/xlm-roberta-base-tweet-sentiment-en): `vocabtrimmer/xlm-roberta-base-tweet-sentiment-en-trimmed-en-50000` 
This model is a trimmed version of [cardiffnlp/xlm-roberta-base-tweet-sentiment-en](https://huggingface.co/cardiffnlp/xlm-roberta-base-tweet-sentiment-en) 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.

|                            | cardiffnlp/xlm-roberta-base-tweet-sentiment-en   | vocabtrimmer/xlm-roberta-base-tweet-sentiment-en-trimmed-en-50000   |
|:---------------------------|:-------------------------------------------------|:--------------------------------------------------------------------|
| parameter_size_full        | 278,045,955                                      | 124,445,955                                                         |
| parameter_size_embedding   | 192,001,536                                      | 38,401,536                                                          |
| vocab_size                 | 250,002                                          | 50,002                                                              |
| compression_rate_full      | 100.0                                            | 44.76                                                               |
| compression_rate_embedding | 100.0                                            | 20.0                                                                |


Following table shows the parameter used to trim vocabulary.

 | language   | dataset                     | dataset_column   | dataset_name   | dataset_split   |   target_vocab_size |   min_frequency |
|:-----------|:----------------------------|:-----------------|:---------------|:----------------|--------------------:|----------------:|
| en         | vocabtrimmer/mc4_validation | text             | en             | validation      |               50000 |               2 |