Upload 7 files
Browse files- .gitattributes +1 -0
- config.json +113 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +3 -0
- tokenizer_config.json +20 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForSequenceClassification"
|
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": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "bg",
|
15 |
+
"1": "hr",
|
16 |
+
"2": "cs",
|
17 |
+
"3": "da",
|
18 |
+
"4": "nl",
|
19 |
+
"5": "en",
|
20 |
+
"6": "et",
|
21 |
+
"7": "fi",
|
22 |
+
"8": "fr",
|
23 |
+
"9": "de",
|
24 |
+
"10": "el",
|
25 |
+
"11": "hu",
|
26 |
+
"12": "it",
|
27 |
+
"13": "lv",
|
28 |
+
"14": "lt",
|
29 |
+
"15": "mt",
|
30 |
+
"16": "no",
|
31 |
+
"17": "pl",
|
32 |
+
"18": "pt",
|
33 |
+
"19": "ro",
|
34 |
+
"20": "sk",
|
35 |
+
"21": "sl",
|
36 |
+
"22": "es",
|
37 |
+
"23": "sv",
|
38 |
+
"24": "ru",
|
39 |
+
"25": "tr",
|
40 |
+
"26": "eu",
|
41 |
+
"27": "ca",
|
42 |
+
"28": "sq",
|
43 |
+
"29": "se",
|
44 |
+
"30": "uk",
|
45 |
+
"31": "ar",
|
46 |
+
"32": "zh",
|
47 |
+
"33": "he",
|
48 |
+
"34": "mhd",
|
49 |
+
"35": "la",
|
50 |
+
"36": "gml",
|
51 |
+
"37": "fro",
|
52 |
+
"38": "chu",
|
53 |
+
"39": "fnhd"
|
54 |
+
},
|
55 |
+
"initializer_range": 0.02,
|
56 |
+
"intermediate_size": 3072,
|
57 |
+
"label2id": {
|
58 |
+
"ar": 31,
|
59 |
+
"bg": 0,
|
60 |
+
"ca": 27,
|
61 |
+
"chu": 38,
|
62 |
+
"cs": 2,
|
63 |
+
"da": 3,
|
64 |
+
"de": 9,
|
65 |
+
"el": 10,
|
66 |
+
"en": 5,
|
67 |
+
"es": 22,
|
68 |
+
"et": 6,
|
69 |
+
"eu": 26,
|
70 |
+
"fi": 7,
|
71 |
+
"fnhd": 39,
|
72 |
+
"fr": 8,
|
73 |
+
"fro": 37,
|
74 |
+
"gml": 36,
|
75 |
+
"he": 33,
|
76 |
+
"hr": 1,
|
77 |
+
"hu": 11,
|
78 |
+
"it": 12,
|
79 |
+
"la": 35,
|
80 |
+
"lt": 14,
|
81 |
+
"lv": 13,
|
82 |
+
"mhd": 34,
|
83 |
+
"mt": 15,
|
84 |
+
"nl": 4,
|
85 |
+
"no": 16,
|
86 |
+
"pl": 17,
|
87 |
+
"pt": 18,
|
88 |
+
"ro": 19,
|
89 |
+
"ru": 24,
|
90 |
+
"se": 29,
|
91 |
+
"sk": 20,
|
92 |
+
"sl": 21,
|
93 |
+
"sq": 28,
|
94 |
+
"sv": 23,
|
95 |
+
"tr": 25,
|
96 |
+
"uk": 30,
|
97 |
+
"zh": 32
|
98 |
+
},
|
99 |
+
"layer_norm_eps": 1e-05,
|
100 |
+
"max_position_embeddings": 514,
|
101 |
+
"model_type": "xlm-roberta",
|
102 |
+
"num_attention_heads": 12,
|
103 |
+
"num_hidden_layers": 12,
|
104 |
+
"output_past": true,
|
105 |
+
"pad_token_id": 1,
|
106 |
+
"position_embedding_type": "absolute",
|
107 |
+
"problem_type": "single_label_classification",
|
108 |
+
"torch_dtype": "float32",
|
109 |
+
"transformers_version": "4.24.0",
|
110 |
+
"type_vocab_size": 1,
|
111 |
+
"use_cache": true,
|
112 |
+
"vocab_size": 250002
|
113 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09ed4c5c65fe8a9c07c43a3d44e4b40990e75679b32b93e2ea801232656f224c
|
3 |
+
size 1112370997
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
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 sha256:62c24cdc13d4c9952d63718d6c9fa4c287974249e16b7ade6d5a85e7bbb75626
|
3 |
+
size 17082660
|
tokenizer_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"__type": "AddedToken",
|
7 |
+
"content": "<mask>",
|
8 |
+
"lstrip": true,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"model_max_length": 512,
|
14 |
+
"name_or_path": "xlm-roberta-base",
|
15 |
+
"pad_token": "<pad>",
|
16 |
+
"sep_token": "</s>",
|
17 |
+
"special_tokens_map_file": null,
|
18 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
19 |
+
"unk_token": "<unk>"
|
20 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9bad4b78207d25b45bac132ff454dbf61f9c03c970c1655f34fe7febc2a6a207
|
3 |
+
size 3387
|