Vocabulary Trimmed xlm-roberta-large: vocabtrimmer/xlm-roberta-large-trimmed-pt-60000
This model is a trimmed version of xlm-roberta-large by vocabtrimmer, a tool for trimming vocabulary of language models to compress the model size.
Following table shows a summary of the trimming process.
| xlm-roberta-large | vocabtrimmer/xlm-roberta-large-trimmed-pt-60000 | |
|---|---|---|
| parameter_size_full | 560,142,482 | 365,392,482 |
| parameter_size_embedding | 256,002,048 | 61,442,048 |
| vocab_size | 250,002 | 60,002 |
| compression_rate_full | 100.0 | 65.23 |
| compression_rate_embedding | 100.0 | 24.0 |
Following table shows the parameter used to trim vocabulary.
| language | dataset | dataset_column | dataset_name | dataset_split | target_vocab_size | min_frequency |
|---|---|---|---|---|---|---|
| pt | vocabtrimmer/mc4_validation | text | pt | validation | 60000 | 2 |
