Text Classification
sentence-transformers
Safetensors
xmod
passage-reranking
antoinelouis commited on
Commit
7a1b8ec
1 Parent(s): a83f2c6

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/xmod-base",
3
+ "adapter_layer_norm": false,
4
+ "adapter_reduction_factor": 2,
5
+ "adapter_reuse_layer_norm": true,
6
+ "architectures": [
7
+ "XmodForSequenceClassification"
8
+ ],
9
+ "attention_probs_dropout_prob": 0.1,
10
+ "bos_token_id": 0,
11
+ "classifier_dropout": null,
12
+ "default_language": "en_XX",
13
+ "eos_token_id": 2,
14
+ "hidden_act": "gelu",
15
+ "hidden_dropout_prob": 0.1,
16
+ "hidden_size": 768,
17
+ "id2label": {
18
+ "0": "LABEL_0"
19
+ },
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 3072,
22
+ "label2id": {
23
+ "LABEL_0": 0
24
+ },
25
+ "languages": [
26
+ "en_XX",
27
+ "id_ID",
28
+ "vi_VN",
29
+ "ru_RU",
30
+ "fa_IR",
31
+ "sv_SE",
32
+ "ja_XX",
33
+ "fr_XX",
34
+ "de_DE",
35
+ "ro_RO",
36
+ "ko_KR",
37
+ "hu_HU",
38
+ "es_XX",
39
+ "fi_FI",
40
+ "uk_UA",
41
+ "da_DK",
42
+ "pt_XX",
43
+ "no_XX",
44
+ "th_TH",
45
+ "pl_PL",
46
+ "bg_BG",
47
+ "nl_XX",
48
+ "zh_CN",
49
+ "he_IL",
50
+ "el_GR",
51
+ "it_IT",
52
+ "sk_SK",
53
+ "hr_HR",
54
+ "tr_TR",
55
+ "ar_AR",
56
+ "cs_CZ",
57
+ "lt_LT",
58
+ "hi_IN",
59
+ "zh_TW",
60
+ "ca_ES",
61
+ "ms_MY",
62
+ "sl_SI",
63
+ "lv_LV",
64
+ "ta_IN",
65
+ "bn_IN",
66
+ "et_EE",
67
+ "az_AZ",
68
+ "sq_AL",
69
+ "sr_RS",
70
+ "kk_KZ",
71
+ "ka_GE",
72
+ "tl_XX",
73
+ "ur_PK",
74
+ "is_IS",
75
+ "hy_AM",
76
+ "ml_IN",
77
+ "mk_MK",
78
+ "be_BY",
79
+ "la_VA",
80
+ "te_IN",
81
+ "eu_ES",
82
+ "gl_ES",
83
+ "mn_MN",
84
+ "kn_IN",
85
+ "ne_NP",
86
+ "sw_KE",
87
+ "si_LK",
88
+ "mr_IN",
89
+ "af_ZA",
90
+ "gu_IN",
91
+ "cy_GB",
92
+ "eo_EO",
93
+ "km_KH",
94
+ "ky_KG",
95
+ "uz_UZ",
96
+ "ps_AF",
97
+ "pa_IN",
98
+ "ga_IE",
99
+ "ha_NG",
100
+ "am_ET",
101
+ "lo_LA",
102
+ "ku_TR",
103
+ "so_SO",
104
+ "my_MM",
105
+ "or_IN",
106
+ "sa_IN"
107
+ ],
108
+ "layer_norm_eps": 1e-05,
109
+ "ln_before_adapter": true,
110
+ "max_position_embeddings": 514,
111
+ "model_type": "xmod",
112
+ "num_attention_heads": 12,
113
+ "num_hidden_layers": 12,
114
+ "pad_token_id": 1,
115
+ "position_embedding_type": "absolute",
116
+ "pre_norm": false,
117
+ "torch_dtype": "float32",
118
+ "transformers_version": "4.36.2",
119
+ "type_vocab_size": 1,
120
+ "use_cache": true,
121
+ "vocab_size": 250002
122
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a9dace2b5429555257f1d09a2ab5fe392364ce781b26e1048e4ff42eee29f36
3
+ size 3410457268
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1cc44ad7faaeec47241864835473fd5403f2da94673f3f764a77ebcb0a803ec
3
+ size 17083009
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "model_max_length": 512,
50
+ "pad_token": "<pad>",
51
+ "sep_token": "</s>",
52
+ "tokenizer_class": "XLMRobertaTokenizer",
53
+ "unk_token": "<unk>"
54
+ }