arnolfokam
commited on
Commit
•
e614862
1
Parent(s):
7d0d594
Second version model
Browse files- config.json +8 -2
- 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
@@ -1,10 +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 |
"gradient_checkpointing": false,
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
@@ -39,10 +40,15 @@
|
|
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": "Davlan/bert-base-multilingual-cased-ner-hrl",
|
3 |
"architectures": [
|
4 |
"BertForTokenClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
"gradient_checkpointing": false,
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout_prob": 0.1,
|
|
|
40 |
"num_attention_heads": 12,
|
41 |
"num_hidden_layers": 12,
|
42 |
"pad_token_id": 0,
|
43 |
+
"pooler_fc_size": 768,
|
44 |
+
"pooler_num_attention_heads": 12,
|
45 |
+
"pooler_num_fc_layers": 3,
|
46 |
+
"pooler_size_per_head": 128,
|
47 |
+
"pooler_type": "first_token_transform",
|
48 |
"position_embedding_type": "absolute",
|
49 |
"torch_dtype": "float32",
|
50 |
"transformers_version": "4.12.5",
|
51 |
"type_vocab_size": 2,
|
52 |
"use_cache": true,
|
53 |
+
"vocab_size": 119547
|
54 |
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b57e92b8958aa76010597453d99ce93a577c331f39030ac9a088e668a277f7b4
|
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":
|
|
|
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, "name_or_path": "Davlan/bert-base-multilingual-cased-ner-hrl", "special_tokens_map_file": "/root/.cache/huggingface/transformers/fc3a79016f096a135e80719eb09df8a9e23a8bafc34c1e8a24a2eab2318e7fc3.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "do_basic_tokenize": true, "never_split": null, "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:d8e711442af68ccac115aadcce8e7e38db8690b4419be622991eb7a4596d8dad
|
3 |
+
size 1455
|
vocab.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|