arnolfokam
commited on
Commit
•
80ad0fa
1
Parent(s):
b5b4f1e
Second version model
Browse files- config.json +8 -3
- pytorch_model.bin +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- training_args.bin +2 -2
- vocab.txt +0 -0
config.json
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "bert-base-cased",
|
3 |
"architectures": [
|
4 |
"BertForTokenClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"classifier_dropout": null,
|
8 |
-
"
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
@@ -39,10 +39,15 @@
|
|
39 |
"num_attention_heads": 12,
|
40 |
"num_hidden_layers": 12,
|
41 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
42 |
"position_embedding_type": "absolute",
|
43 |
"torch_dtype": "float32",
|
44 |
"transformers_version": "4.12.5",
|
45 |
"type_vocab_size": 2,
|
46 |
"use_cache": true,
|
47 |
-
"vocab_size":
|
48 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "bert-base-multilingual-cased",
|
3 |
"architectures": [
|
4 |
"BertForTokenClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
"hidden_size": 768,
|
|
|
39 |
"num_attention_heads": 12,
|
40 |
"num_hidden_layers": 12,
|
41 |
"pad_token_id": 0,
|
42 |
+
"pooler_fc_size": 768,
|
43 |
+
"pooler_num_attention_heads": 12,
|
44 |
+
"pooler_num_fc_layers": 3,
|
45 |
+
"pooler_size_per_head": 128,
|
46 |
+
"pooler_type": "first_token_transform",
|
47 |
"position_embedding_type": "absolute",
|
48 |
"torch_dtype": "float32",
|
49 |
"transformers_version": "4.12.5",
|
50 |
"type_vocab_size": 2,
|
51 |
"use_cache": true,
|
52 |
+
"vocab_size": 119547
|
53 |
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1ddbd7fa3253e4ed6f825e2f7cf24d6d84f718ebecab87e238e00e80b0b7b8a
|
3 |
+
size 709162481
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-cased", "tokenizer_class": "BertTokenizer"}
|
|
|
1 |
+
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-multilingual-cased", "tokenizer_class": "BertTokenizer"}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5edff7ccdf925db527812b5527a07489a24f9355c01a0a454862de97696cd88
|
3 |
+
size 1455
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|