Hugging Face's logo

token-classifier
/
roBERTa-v2

Token Classification
Transformers
PyTorch
roberta
Generated from Trainer
Eval Results
Model card Files Community
1
suyashmittal commited on
Commit
931e384
·
1 Parent(s): 4536372

Training in progress, epoch 0

Browse files
Files changed (8) hide show
  1. config.json +10 -9
  2. merges.txt +0 -0
  3. pytorch_model.bin +2 -2
  4. special_tokens_map.json +13 -5
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +11 -9
  7. training_args.bin +1 -1
  8. vocab.json +0 -0
config.json CHANGED
@@ -1,11 +1,12 @@
1
  {
2
- "_name_or_path": "bert-large-uncased",
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": 1024,
@@ -41,16 +42,16 @@
41
  "I-no": 2,
42
  "O": 0
43
  },
44
- "layer_norm_eps": 1e-12,
45
- "max_position_embeddings": 512,
46
- "model_type": "bert",
47
  "num_attention_heads": 16,
48
  "num_hidden_layers": 24,
49
- "pad_token_id": 0,
50
  "position_embedding_type": "absolute",
51
  "torch_dtype": "float32",
52
  "transformers_version": "4.33.2",
53
- "type_vocab_size": 2,
54
  "use_cache": true,
55
- "vocab_size": 30522
56
  }
 
1
  {
2
+ "_name_or_path": "roberta-large",
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": 1024,
 
42
  "I-no": 2,
43
  "O": 0
44
  },
45
+ "layer_norm_eps": 1e-05,
46
+ "max_position_embeddings": 514,
47
+ "model_type": "roberta",
48
  "num_attention_heads": 16,
49
  "num_hidden_layers": 24,
50
+ "pad_token_id": 1,
51
  "position_embedding_type": "absolute",
52
  "torch_dtype": "float32",
53
  "transformers_version": "4.33.2",
54
+ "type_vocab_size": 1,
55
  "use_cache": true,
56
+ "vocab_size": 50265
57
  }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:032a0ac90844a598c905e299733e0c3315e844b8950f8388c0085500d193874c
3
- size 1336556201
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0a385552aef37110d73c124ec9f852b82bec02b30128caf95492540ebe544e7
3
+ size 1417428777
special_tokens_map.json CHANGED
@@ -1,7 +1,15 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
7
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,13 +1,15 @@
1
  {
 
 
2
  "clean_up_tokenization_spaces": true,
3
- "cls_token": "[CLS]",
4
- "do_lower_case": true,
5
- "mask_token": "[MASK]",
 
6
  "model_max_length": 512,
7
- "pad_token": "[PAD]",
8
- "sep_token": "[SEP]",
9
- "strip_accents": null,
10
- "tokenize_chinese_chars": true,
11
- "tokenizer_class": "BertTokenizer",
12
- "unk_token": "[UNK]"
13
  }
 
1
  {
2
+ "add_prefix_space": true,
3
+ "bos_token": "<s>",
4
  "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
  "model_max_length": 512,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "RobertaTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
 
15
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3752b9b251ed68acd4afa15ecf6ef94dba7993b3122c5c200fe1487b6925fc5
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39aa12d85e488381487d7ec5d67c4ca9f37c095f50415203129b922a68756564
3
  size 4027
vocab.json ADDED
The diff for this file is too large to render. See raw diff