Vocabulary Trimmed cardiffnlp/xlm-v-base-tweet-sentiment-pt: vocabtrimmer/xlm-v-base-tweet-sentiment-pt-trimmed-pt
This model is a trimmed version of cardiffnlp/xlm-v-base-tweet-sentiment-pt by vocabtrimmer, a tool for trimming vocabulary of language models to compress the model size.
Following table shows a summary of the trimming process.
| cardiffnlp/xlm-v-base-tweet-sentiment-pt | vocabtrimmer/xlm-v-base-tweet-sentiment-pt-trimmed-pt | |
|---|---|---|
| parameter_size_full | 778,495,491 | 225,338,883 |
| parameter_size_embedding | 692,451,072 | 139,294,464 |
| vocab_size | 901,629 | 181,373 |
| compression_rate_full | 100.0 | 28.95 |
| compression_rate_embedding | 100.0 | 20.12 |
Following table shows the parameter used to trim vocabulary.
| language | dataset | dataset_column | dataset_name | dataset_split | target_vocab_size | min_frequency |
|---|---|---|---|---|---|---|
| pt | vocabtrimmer/mc4_validation | text | pt | validation | 2 |
