Vocabulary Trimmed facebook/mbart-large-cc25: vocabtrimmer/mbart-large-cc25-trimmed-fr
This model is a trimmed version of facebook/mbart-large-cc25 by vocabtrimmer
, a tool for trimming vocabulary of language models to compress the model size.
Following table shows a summary of the trimming process.
facebook/mbart-large-cc25 | vocabtrimmer/mbart-large-cc25-trimmed-fr | |
---|---|---|
parameter_size_full | 610,851,840 | 442,610,688 |
parameter_size_embedding | 512,055,296 | 175,572,992 |
vocab_size | 250,027 | 85,729 |
compression_rate_full | 100.0 | 72.46 |
compression_rate_embedding | 100.0 | 34.29 |
Following table shows the parameter used to trim vocabulary.
language | dataset | dataset_column | dataset_name | dataset_split | target_vocab_size | min_frequency |
---|---|---|---|---|---|---|
fr | vocabtrimmer/mc4_validation | text | fr | validation | 2 |