mt5-base-trimmed-es / README.md
asahi417's picture
commit files to HF hub
05fb701
# Vocabulary Trimmed [google/mt5-base](https://huggingface.co/google/mt5-base): `vocabtrimmer/mt5-base-trimmed-es`
This model is a trimmed version of [google/mt5-base](https://huggingface.co/google/mt5-base) by [`vocabtrimmer`](https://github.com/asahi417/lm-vocab-trimmer), 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-es |
|:---------------------------|:------------------|:-----------------------------------|
| parameter_size_full | 582,401,280 | 399,606,528 |
| parameter_size_embedding | 384,172,032 | 201,377,280 |
| vocab_size | 250,112 | 131,105 |
| compression_rate_full | 100.0 | 68.61 |
| 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 |