Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: ["hi"]
|
| 3 |
+
tags:
|
| 4 |
+
- hindi
|
| 5 |
+
license: mit
|
| 6 |
+
---
|
| 7 |
+
This is a smaller version of the [google/mt5-base](https://huggingface.co/google/mt5-base) model with only hindi embeddings left.
|
| 8 |
+
* The original model has 582M parameters, with 237M of them being input and output embeddings.
|
| 9 |
+
* After shrinking the `sentencepiece` vocabulary from 250K to 25K (top 25K Hindi tokens) the number of model parameters reduced to 237M parameters, and model size reduced from 2.2GB to 0.9GB - 42% of the original one.
|
| 10 |
+
## Citing & Authors
|
| 11 |
+
- Model : [google/mt5-base](https://huggingface.co/google/mt5-base)
|
| 12 |
+
- Reference: [cointegrated/rut5-base](https://huggingface.co/cointegrated/rut5-base)
|