model: add PyTorch and TensorFlow weights for new Italian ELECTRA model (trained on mC4)
Browse files- config.json +27 -0
- pytorch_model.bin +3 -0
- tf_model.h5 +3 -0
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./",
|
3 |
+
"architectures": [
|
4 |
+
"ElectraForPreTraining"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"embedding_size": 768,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 512,
|
15 |
+
"model_type": "electra",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"summary_activation": "gelu",
|
21 |
+
"summary_last_dropout": 0.1,
|
22 |
+
"summary_type": "first",
|
23 |
+
"summary_use_proj": true,
|
24 |
+
"transformers_version": "4.9.2",
|
25 |
+
"type_vocab_size": 2,
|
26 |
+
"vocab_size": 31102
|
27 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ecebb0b5393e02d0432a0727fbda379398247d3dafef6e0c91cff414f30e77d5
|
3 |
+
size 439796397
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a032d78467cba1df98bdc56dc796fc49b9b6a31adf48ebd85d5f89966f1ce83
|
3 |
+
size 439987472
|