Vocabulary Trimmed lmqg/mt5-small-esquad-qg: vocabtrimmer/mt5-small-esquad-qg-trimmed
This model is a trimmed version of lmqg/mt5-small-esquad-qg by vocabtrimmer, a tool for trimming vocabulary of language models to compress the model size.
Following table shows a summary of the trimming process.
| lmqg/mt5-small-esquad-qg | vocabtrimmer/mt5-small-esquad-qg-trimmed | |
|---|---|---|
| parameter_size_full | 300,165,504 | 178,314,624 |
| parameter_size_embedding | 256,103,424 | 134,252,544 |
| vocab_size | 250,101 | 131,106 |
| compression_rate_full | 100.0 | 59.41 |
| compression_rate_embedding | 100.0 | 52.42 |
Following table shows the parameter used to trim vocabulary.
| language | dataset | dataset_column | dataset_name | dataset_split | target_vocab_size | min_frequency |
|---|---|---|---|---|---|---|
| es | vocabtrimmer/mc4_validation | text | es | validation | 2 |
