Vocabulary Trimmed vocabtrimmer/xlm-roberta-base-xnli-de: vocabtrimmer/xlm-roberta-base-xnli-de-trimmed-de-5000
This model is a trimmed version of vocabtrimmer/xlm-roberta-base-xnli-de by vocabtrimmer, a tool for trimming vocabulary of language models to compress the model size.
Following table shows a summary of the trimming process.
| vocabtrimmer/xlm-roberta-base-xnli-de | vocabtrimmer/xlm-roberta-base-xnli-de-trimmed-de-5000 | |
|---|---|---|
| parameter_size_full | 278,045,955 | 89,885,955 |
| parameter_size_embedding | 192,001,536 | 3,841,536 |
| vocab_size | 250,002 | 5,002 |
| compression_rate_full | 100.0 | 32.33 |
| 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 |
|---|---|---|---|---|---|---|
| de | vocabtrimmer/mc4_validation | text | de | validation | 5000 | 2 |