alex-atelo
commited on
Commit
•
f579828
1
Parent(s):
c68b710
Add config.json
Browse files- README.md +3 -3
- config.json +23 -0
README.md
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
---
|
2 |
-
language:
|
3 |
- en
|
4 |
-
|
5 |
tags:
|
6 |
- question-answering
|
7 |
-
license: apache-2.0
|
8 |
datasets:
|
9 |
- squad
|
10 |
metrics:
|
11 |
- squad
|
|
|
12 |
---
|
13 |
|
14 |
# DistilBERT with a second step of distillation
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
- en
|
4 |
+
license: apache-2.0
|
5 |
tags:
|
6 |
- question-answering
|
|
|
7 |
datasets:
|
8 |
- squad
|
9 |
metrics:
|
10 |
- squad
|
11 |
+
thumbnail: https://github.com/karanchahal/distiller/blob/master/distiller.jpg
|
12 |
---
|
13 |
|
14 |
# DistilBERT with a second step of distillation
|
config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForMaskedLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"qa_dropout": 0.1,
|
18 |
+
"seq_classif_dropout": 0.2,
|
19 |
+
"sinusoidal_pos_embds": false,
|
20 |
+
"tie_weights_": true,
|
21 |
+
"transformers_version": "4.38.2",
|
22 |
+
"vocab_size": 30522
|
23 |
+
}
|