arnolfokam commited on
Commit
02ec0a7
1 Parent(s): fb5dfd8

Second version model

Browse files
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
- "gradient_checkpointing": false,
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": 28996
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:a2e563fe9406fa739a89f15de07c9da4f1b5fd5fa2eb880cde59e68d68ddcd40
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:dbfbabecef26c7df743e363ec74624f39056614445cef6edfbaec8d0f36951e5
3
- size 1391
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:899b7bea791108d474c244ffe00072d8a577830c4b31a9ee39b76a81c84cd540
3
+ size 1455
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff