arnolfokam commited on
Commit
79ba66f
1 Parent(s): 1283ba3

Second version model

Browse files
config.json CHANGED
@@ -1,11 +1,12 @@
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,
@@ -33,16 +34,16 @@
33
  "I-PER": 4,
34
  "O": 0
35
  },
36
- "layer_norm_eps": 1e-12,
37
- "max_position_embeddings": 512,
38
- "model_type": "bert",
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": "roberta-base",
3
  "architectures": [
4
+ "RobertaForTokenClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
  "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
  "hidden_act": "gelu",
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
 
34
  "I-PER": 4,
35
  "O": 0
36
  },
37
+ "layer_norm_eps": 1e-05,
38
+ "max_position_embeddings": 514,
39
+ "model_type": "roberta",
40
  "num_attention_heads": 12,
41
  "num_hidden_layers": 12,
42
+ "pad_token_id": 1,
43
  "position_embedding_type": "absolute",
44
  "torch_dtype": "float32",
45
  "transformers_version": "4.12.5",
46
+ "type_vocab_size": 1,
47
  "use_cache": true,
48
+ "vocab_size": 50265
49
  }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:751e62d460acbcd867f46e8ec8cada468ca9f305aacb91cd392273613cb069ae
3
+ size 496332529
special_tokens_map.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
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
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}
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 sha256:8d19e27c754207ce11a3dc347d82948b6751e6e6daf946317a186607e00c295a
3
+ size 1455
vocab.json ADDED
The diff for this file is too large to render. See raw diff