Views
No views yet
vocabtrimmer/mt5-base-trimmed-frvocabtrimmer, 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 | |
|---|---|---|
| parameter_size_full | 582,401,280 | 399,577,344 |
| parameter_size_embedding | 384,172,032 | 201,348,096 |
| vocab_size | 250,112 | 131,086 |
| compression_rate_full | 100.0 | 68.61 |
| compression_rate_embedding | 100.0 | 52.41 |
| language | dataset | dataset_column | dataset_name | dataset_split | target_vocab_size | min_frequency |
|---|---|---|---|---|---|---|
| fr | vocabtrimmer/mc4_validation | text | fr | validation | 2 |