commit files to HF hub

README.md

@@ -0,0 +1,18 @@
+# Vocabulary Trimmed [google/mt5-base](https://huggingface.co/google/mt5-base): `vocabtrimmer/mt5-base-trimmed-ko-15000` 
+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-ko-15000   |
+|:---------------------------|:------------------|:-----------------------------------------|
+| parameter_size_full        | 582,401,280       | 221,270,784                              |
+| parameter_size_embedding   | 384,172,032       | 23,041,536                               |
+| vocab_size                 | 250,112           | 15,001                                   |
+| compression_rate_full      | 100.0             | 37.99                                    |
+| compression_rate_embedding | 100.0             | 6.0                                      |
+
+
+Following table shows the parameter used to trim vocabulary.
+
+ | language   | dataset                     | dataset_column   | dataset_name   | dataset_split   |   target_vocab_size |   min_frequency |
+|:-----------|:----------------------------|:-----------------|:---------------|:----------------|--------------------:|----------------:|
+| ko         | vocabtrimmer/mc4_validation | text             | ko             | validation      |               15000 |               2 |