assenmacher commited on
Commit
a308dc4
1 Parent(s): fcb992d

Upload 6 files

Browse files
Files changed (6) hide show
  1. config.json +101 -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 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "flaubert/flaubert_small_cased",
3
+ "amp": 1,
4
+ "architectures": [
5
+ "FlaubertForSequenceClassification"
6
+ ],
7
+ "asm": false,
8
+ "attention_dropout": 0.1,
9
+ "bos_index": 0,
10
+ "bos_token_id": 0,
11
+ "bptt": 512,
12
+ "causal": false,
13
+ "clip_grad_norm": 5,
14
+ "dropout": 0.1,
15
+ "emb_dim": 512,
16
+ "embed_init_std": 0.02209708691207961,
17
+ "encoder_only": true,
18
+ "end_n_top": 5,
19
+ "eos_index": 1,
20
+ "fp16": true,
21
+ "gelu_activation": true,
22
+ "group_by_size": true,
23
+ "id2label": {
24
+ "0": "LABEL_0",
25
+ "1": "LABEL_1",
26
+ "2": "LABEL_2",
27
+ "3": "LABEL_3",
28
+ "4": "LABEL_4",
29
+ "5": "LABEL_5",
30
+ "6": "LABEL_6",
31
+ "7": "LABEL_7"
32
+ },
33
+ "id2lang": {
34
+ "0": "fr"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2,
42
+ "LABEL_3": 3,
43
+ "LABEL_4": 4,
44
+ "LABEL_5": 5,
45
+ "LABEL_6": 6,
46
+ "LABEL_7": 7
47
+ },
48
+ "lang2id": {
49
+ "fr": 0
50
+ },
51
+ "lang_id": 0,
52
+ "langs": [
53
+ "fr"
54
+ ],
55
+ "layer_norm_eps": 1e-06,
56
+ "layerdrop": 0.2,
57
+ "lg_sampling_factor": -1,
58
+ "lgs": "fr",
59
+ "mask_index": 5,
60
+ "mask_token_id": 0,
61
+ "max_batch_size": 0,
62
+ "max_position_embeddings": 512,
63
+ "max_vocab": -1,
64
+ "mlm_steps": [
65
+ [
66
+ "fr",
67
+ null
68
+ ]
69
+ ],
70
+ "model_type": "flaubert",
71
+ "n_heads": 8,
72
+ "n_langs": 1,
73
+ "n_layers": 6,
74
+ "pad_index": 2,
75
+ "pad_token_id": 2,
76
+ "pre_norm": true,
77
+ "problem_type": "single_label_classification",
78
+ "sample_alpha": 0,
79
+ "share_inout_emb": true,
80
+ "sinusoidal_embeddings": false,
81
+ "start_n_top": 5,
82
+ "summary_activation": null,
83
+ "summary_first_dropout": 0.1,
84
+ "summary_proj_to_labels": true,
85
+ "summary_type": "first",
86
+ "summary_use_proj": true,
87
+ "tokens_per_batch": -1,
88
+ "torch_dtype": "float32",
89
+ "transformers_version": "4.27.4",
90
+ "unk_index": 3,
91
+ "use_lang_emb": true,
92
+ "vocab_size": 68729,
93
+ "word_blank": 0,
94
+ "word_dropout": 0,
95
+ "word_keep": 0.1,
96
+ "word_mask": 0.8,
97
+ "word_mask_keep_rand": "0.8,0.1,0.1",
98
+ "word_pred": 0.15,
99
+ "word_rand": 0.1,
100
+ "word_shuffle": 0
101
+ }
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:e371667a79c3f1271340cce14e28a25c359d57548e40b858ff1027b55168ae95
3
+ size 217516517
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
+ "cls_token": "</s>",
16
+ "do_lower_case": false,
17
+ "id2lang": null,
18
+ "lang2id": null,
19
+ "mask_token": "<special1>",
20
+ "model_max_length": 512,
21
+ "pad_token": "<pad>",
22
+ "sep_token": "</s>",
23
+ "special_tokens_map_file": null,
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