Vocabulary Trimmed google/mt5-base: vocabtrimmer/mt5-base-trimmed-fr-60000
This model is a trimmed version of google/mt5-base by vocabtrimmer, a tool for trimming vocabulary of language models to compress the model size.
Following table shows a summary of the trimming process.
| google/mt5-base | vocabtrimmer/mt5-base-trimmed-fr-60000 | |
|---|---|---|
| parameter_size_full | 582,401,280 | 290,390,784 |
| parameter_size_embedding | 384,172,032 | 92,161,536 |
| vocab_size | 250,112 | 60,001 |
| compression_rate_full | 100.0 | 49.86 |
| compression_rate_embedding | 100.0 | 23.99 |
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 | 60000 | 2 |
