ilovebots commited on
Commit
9c116c3
1 Parent(s): 506f950

Upload 6 files

Browse files
Files changed (6) hide show
  1. config.json +132 -0
  2. merges.txt +0 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +20 -0
  5. tokenizer_config.json +26 -0
  6. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,132 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "flaubert/flaubert_large_cased",
3
+ "amp": 1,
4
+ "architectures": [
5
+ "BertForSequenceClassification"
6
+ ],
7
+ "asm": false,
8
+ "attention_dropout": 0.1,
9
+ "attention_probs_dropout_prob": 0.1,
10
+ "bos_index": 0,
11
+ "bos_token_id": 0,
12
+ "bptt": 512,
13
+ "causal": false,
14
+ "classifier_dropout": null,
15
+ "clip_grad_norm": 5,
16
+ "dropout": 0.1,
17
+ "emb_dim": 1024,
18
+ "embed_init_std": 0.02209708691207961,
19
+ "encoder_only": true,
20
+ "end_n_top": 5,
21
+ "eos_index": 1,
22
+ "fp16": true,
23
+ "gelu_activation": true,
24
+ "group_by_size": true,
25
+ "hidden_act": "gelu",
26
+ "hidden_dropout_prob": 0.1,
27
+ "hidden_size": 768,
28
+ "id2label": {
29
+ "0": "LABEL_0",
30
+ "1": "LABEL_1",
31
+ "2": "LABEL_2",
32
+ "3": "LABEL_3",
33
+ "4": "LABEL_4",
34
+ "5": "LABEL_5",
35
+ "6": "LABEL_6",
36
+ "7": "LABEL_7",
37
+ "8": "LABEL_8",
38
+ "9": "LABEL_9",
39
+ "10": "LABEL_10",
40
+ "11": "LABEL_11",
41
+ "12": "LABEL_12",
42
+ "13": "LABEL_13",
43
+ "14": "LABEL_14",
44
+ "15": "LABEL_15",
45
+ "16": "LABEL_16"
46
+ },
47
+ "id2lang": {
48
+ "0": "fr"
49
+ },
50
+ "init_std": 0.02,
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 3072,
53
+ "is_encoder": true,
54
+ "label2id": {
55
+ "LABEL_0": 0,
56
+ "LABEL_1": 1,
57
+ "LABEL_10": 10,
58
+ "LABEL_11": 11,
59
+ "LABEL_12": 12,
60
+ "LABEL_13": 13,
61
+ "LABEL_14": 14,
62
+ "LABEL_15": 15,
63
+ "LABEL_16": 16,
64
+ "LABEL_2": 2,
65
+ "LABEL_3": 3,
66
+ "LABEL_4": 4,
67
+ "LABEL_5": 5,
68
+ "LABEL_6": 6,
69
+ "LABEL_7": 7,
70
+ "LABEL_8": 8,
71
+ "LABEL_9": 9
72
+ },
73
+ "lang2id": {
74
+ "fr": 0
75
+ },
76
+ "lang_id": 0,
77
+ "langs": [
78
+ "fr"
79
+ ],
80
+ "layer_norm_eps": 1e-06,
81
+ "layerdrop": 0.2,
82
+ "lg_sampling_factor": -1,
83
+ "lgs": "fr",
84
+ "mask_index": 5,
85
+ "mask_token_id": 0,
86
+ "max_batch_size": 0,
87
+ "max_position_embeddings": 512,
88
+ "max_vocab": -1,
89
+ "mlm_steps": [
90
+ [
91
+ "fr",
92
+ null
93
+ ]
94
+ ],
95
+ "model_type": "bert",
96
+ "n_heads": 16,
97
+ "n_langs": 1,
98
+ "n_layers": 24,
99
+ "num_attention_heads": 12,
100
+ "num_hidden_layers": 12,
101
+ "pad_index": 2,
102
+ "pad_token_id": 2,
103
+ "position_embedding_type": "absolute",
104
+ "pre_norm": true,
105
+ "problem_type": "single_label_classification",
106
+ "sample_alpha": 0,
107
+ "share_inout_emb": true,
108
+ "sinusoidal_embeddings": false,
109
+ "start_n_top": 5,
110
+ "summary_activation": null,
111
+ "summary_first_dropout": 0.1,
112
+ "summary_proj_to_labels": true,
113
+ "summary_type": "first",
114
+ "summary_use_proj": true,
115
+ "tokens_per_batch": -1,
116
+ "torch_dtype": "float32",
117
+ "transformers_version": "4.30.2",
118
+ "type_vocab_size": 2,
119
+ "unk_index": 3,
120
+ "use_apex": true,
121
+ "use_cache": true,
122
+ "use_lang_emb": true,
123
+ "vocab_size": 68729,
124
+ "word_blank": 0,
125
+ "word_dropout": 0,
126
+ "word_keep": 0.1,
127
+ "word_mask": 0.8,
128
+ "word_mask_keep_rand": "0.8,0.1,0.1",
129
+ "word_pred": 0.15,
130
+ "word_rand": 0.1,
131
+ "word_shuffle": 0
132
+ }
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:b03123e7f5490732c5e75a959d4e59070f87d67b9989f55d26bff9432680fa70
3
+ size 555425973
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<special0>",
4
+ "<special1>",
5
+ "<special2>",
6
+ "<special3>",
7
+ "<special4>",
8
+ "<special5>",
9
+ "<special6>",
10
+ "<special7>",
11
+ "<special8>",
12
+ "<special9>"
13
+ ],
14
+ "bos_token": "<s>",
15
+ "cls_token": "</s>",
16
+ "mask_token": "<special1>",
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "unk_token": "<unk>"
20
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<special0>",
4
+ "<special1>",
5
+ "<special2>",
6
+ "<special3>",
7
+ "<special4>",
8
+ "<special5>",
9
+ "<special6>",
10
+ "<special7>",
11
+ "<special8>",
12
+ "<special9>"
13
+ ],
14
+ "bos_token": "<s>",
15
+ "clean_up_tokenization_spaces": true,
16
+ "cls_token": "</s>",
17
+ "do_lower_case": false,
18
+ "id2lang": null,
19
+ "lang2id": null,
20
+ "mask_token": "<special1>",
21
+ "model_max_length": 512,
22
+ "pad_token": "<pad>",
23
+ "sep_token": "</s>",
24
+ "tokenizer_class": "FlaubertTokenizer",
25
+ "unk_token": "<unk>"
26
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff