EhimeNLP commited on
Commit
9cc82b7
·
verified ·
1 Parent(s): efe3969

Upload 6 files

Browse files
config.json CHANGED
@@ -3,24 +3,24 @@
3
  "RobertaForMaskedLM"
4
  ],
5
  "attention_probs_dropout_prob": 0.1,
6
- "bos_token_id": 2,
7
  "classifier_dropout": null,
8
- "eos_token_id": 3,
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 3072,
14
- "layer_norm_eps": 1e-12,
15
  "max_position_embeddings": 514,
16
  "model_type": "roberta",
17
  "num_attention_heads": 12,
18
  "num_hidden_layers": 12,
19
- "pad_token_id": 0,
20
  "position_embedding_type": "absolute",
21
  "torch_dtype": "float32",
22
- "transformers_version": "4.12.5",
23
- "type_vocab_size": 2,
24
  "use_cache": true,
25
  "vocab_size": 32017
26
  }
 
3
  "RobertaForMaskedLM"
4
  ],
5
  "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
  "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
  "max_position_embeddings": 514,
16
  "model_type": "roberta",
17
  "num_attention_heads": 12,
18
  "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
  "position_embedding_type": "absolute",
21
  "torch_dtype": "float32",
22
+ "transformers_version": "4.42.4",
23
+ "type_vocab_size": 1,
24
  "use_cache": true,
25
  "vocab_size": 32017
26
  }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0711f34bf5a0bfed9bfeba33a3be6bd2544d52f50900b4f445ad88c2a85d0120
3
+ size 442811256
special_tokens_map.json CHANGED
@@ -1 +1,15 @@
1
- {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 +1,57 @@
1
- {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "mask_token": "<mask>", "tokenizer_class": "PreTrainedTokenizerFast"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32016": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
unigram.json ADDED
The diff for this file is too large to render. See raw diff