model_700000
Browse files- config.json +25 -0
- pytorch_model.bin +3 -0
- tf_model.h5 +3 -0
- tokenizer_config.json +5 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "input_models",
|
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 |
+
"summary_activation": "gelu",
|
20 |
+
"summary_last_dropout": 0.1,
|
21 |
+
"summary_type": "first",
|
22 |
+
"summary_use_proj": true,
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"vocab_size": 42000
|
25 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8c5e1cb7459152f039354e6eddd63ba330c66edd205d0d31bc54e02e6ebb649
|
3 |
+
size 473243447
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29f4b481aecdb017ee7bc093dc14fd454ffec06aeaf8b473ca6572d3562e193a
|
3 |
+
size 471087912
|
tokenizer_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_lower_case": true,
|
3 |
+
"strip_accents": false,
|
4 |
+
"model_max_length": 512
|
5 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|