Add README
Browse files
README.md
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# BERT Base for Tigrinya Language
|
| 2 |
+
|
| 3 |
+
We pretrain a BERT base-uncased model on a relatively small dataset for Tigrinya (34M tokens) for 40 epochs.
|
| 4 |
+
|
| 5 |
+
Contained in this card is a PyTorch model exported from the original model that was trained on a TPU v3.8 with Flax.
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
## Hyperparameters
|
| 9 |
+
|
| 10 |
+
The hyperparameters corresponding to model sizes mentioned above are as follows:
|
| 11 |
+
|
| 12 |
+
| Model Size | L | AH | HS | FFN | P |
|
| 13 |
+
|------------|----|----|-----|------|------|
|
| 14 |
+
| BASE | 12 | 12 | 768 | 3072 | 110M |
|
| 15 |
+
|
| 16 |
+
(L = number of layers; AH = number of attention heads; HS = hidden size; FFN = feedforward network dimension; P = number of parameters.)
|
| 17 |
+
|
| 18 |
+
|