commit files to HF hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Vocabulary Trimmed [google/mt5-base](https://huggingface.co/google/mt5-base): `vocabtrimmer/mt5-base-trimmed-ko-30000`
|
| 2 |
+
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.
|
| 3 |
+
Following table shows a summary of the trimming process.
|
| 4 |
+
|
| 5 |
+
| | google/mt5-base | vocabtrimmer/mt5-base-trimmed-ko-30000 |
|
| 6 |
+
|:---------------------------|:------------------|:-----------------------------------------|
|
| 7 |
+
| parameter_size_full | 582,401,280 | 244,310,784 |
|
| 8 |
+
| parameter_size_embedding | 384,172,032 | 46,081,536 |
|
| 9 |
+
| vocab_size | 250,112 | 30,001 |
|
| 10 |
+
| compression_rate_full | 100.0 | 41.95 |
|
| 11 |
+
| compression_rate_embedding | 100.0 | 12.0 |
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
Following table shows the parameter used to trim vocabulary.
|
| 15 |
+
|
| 16 |
+
| language | dataset | dataset_column | dataset_name | dataset_split | target_vocab_size | min_frequency |
|
| 17 |
+
|:-----------|:----------------------------|:-----------------|:---------------|:----------------|--------------------:|----------------:|
|
| 18 |
+
| ko | vocabtrimmer/mc4_validation | text | ko | validation | 30000 | 2 |
|