Add size details
Browse files
README.md
CHANGED
|
@@ -36,6 +36,16 @@ classifier using the features produced by the ALBERT model as inputs.
|
|
| 36 |
|
| 37 |
ALBERT is particular in that it shares its layers across its Transformer. Therefore, all layers have the same weights. Using repeating layers results in a small memory footprint, however, the computational cost remains similar to a BERT-like architecture with the same number of hidden layers as it has to iterate through the same number of (repeating) layers.
|
| 38 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
## Intended uses & limitations
|
| 40 |
|
| 41 |
You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to
|
|
|
|
| 36 |
|
| 37 |
ALBERT is particular in that it shares its layers across its Transformer. Therefore, all layers have the same weights. Using repeating layers results in a small memory footprint, however, the computational cost remains similar to a BERT-like architecture with the same number of hidden layers as it has to iterate through the same number of (repeating) layers.
|
| 38 |
|
| 39 |
+
This is the second version of the base model. Version 2 is different from version 1 due to different dropout rates, additional training data, and longer training. It has better results in nearly all downstream tasks.
|
| 40 |
+
|
| 41 |
+
This model has the following configuration:
|
| 42 |
+
|
| 43 |
+
- 12 repeating layers
|
| 44 |
+
- 128 embedding dimension
|
| 45 |
+
- 768 hidden dimension
|
| 46 |
+
- 12 attention heads
|
| 47 |
+
- 11M parameters
|
| 48 |
+
|
| 49 |
## Intended uses & limitations
|
| 50 |
|
| 51 |
You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to
|