| # Vocabulary Trimmed [facebook/xlm-v-base](https://huggingface.co/facebook/xlm-v-base): `vocabtrimmer/xlm-v-base-trimmed-en` | |
| This model is a trimmed version of [facebook/xlm-v-base](https://huggingface.co/facebook/xlm-v-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. | |
| | | facebook/xlm-v-base | vocabtrimmer/xlm-v-base-trimmed-en | | |
| |:---------------------------|:----------------------|:-------------------------------------| | |
| | parameter_size_full | 779,396,349 | 458,814,091 | | |
| | parameter_size_embedding | 692,451,072 | 372,285,696 | | |
| | vocab_size | 901,629 | 484,747 | | |
| | compression_rate_full | 100.0 | 58.87 | | |
| | compression_rate_embedding | 100.0 | 53.76 | | |
| 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 | | 2 | |