# Vocabulary Trimmed [cardiffnlp/xlm-v-base-tweet-sentiment-fr](https://huggingface.co/cardiffnlp/xlm-v-base-tweet-sentiment-fr): `vocabtrimmer/xlm-v-base-tweet-sentiment-fr-trimmed-fr` 
This model is a trimmed version of [cardiffnlp/xlm-v-base-tweet-sentiment-fr](https://huggingface.co/cardiffnlp/xlm-v-base-tweet-sentiment-fr) 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.

|                            | cardiffnlp/xlm-v-base-tweet-sentiment-fr   | vocabtrimmer/xlm-v-base-tweet-sentiment-fr-trimmed-fr   |
|:---------------------------|:-------------------------------------------|:--------------------------------------------------------|
| parameter_size_full        | 778,495,491                                | 253,812,483                                             |
| parameter_size_embedding   | 692,451,072                                | 167,768,064                                             |
| vocab_size                 | 901,629                                    | 218,448                                                 |
| compression_rate_full      | 100.0                                      | 32.6                                                    |
| compression_rate_embedding | 100.0                                      | 24.23                                                   |


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      |                     |               2 |