Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- config.json +130 -0
- model-001.safetensors +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +61 -0
.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 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./XLM-RoBERTa",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForTokenClassification"
|
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": 1024,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6",
|
21 |
+
"7": "LABEL_7",
|
22 |
+
"8": "LABEL_8",
|
23 |
+
"9": "LABEL_9",
|
24 |
+
"10": "LABEL_10",
|
25 |
+
"11": "LABEL_11",
|
26 |
+
"12": "LABEL_12",
|
27 |
+
"13": "LABEL_13",
|
28 |
+
"14": "LABEL_14",
|
29 |
+
"15": "LABEL_15",
|
30 |
+
"16": "LABEL_16",
|
31 |
+
"17": "LABEL_17",
|
32 |
+
"18": "LABEL_18",
|
33 |
+
"19": "LABEL_19",
|
34 |
+
"20": "LABEL_20",
|
35 |
+
"21": "LABEL_21",
|
36 |
+
"22": "LABEL_22",
|
37 |
+
"23": "LABEL_23",
|
38 |
+
"24": "LABEL_24",
|
39 |
+
"25": "LABEL_25",
|
40 |
+
"26": "LABEL_26",
|
41 |
+
"27": "LABEL_27",
|
42 |
+
"28": "LABEL_28",
|
43 |
+
"29": "LABEL_29",
|
44 |
+
"30": "LABEL_30",
|
45 |
+
"31": "LABEL_31",
|
46 |
+
"32": "LABEL_32",
|
47 |
+
"33": "LABEL_33",
|
48 |
+
"34": "LABEL_34",
|
49 |
+
"35": "LABEL_35",
|
50 |
+
"36": "LABEL_36",
|
51 |
+
"37": "LABEL_37",
|
52 |
+
"38": "LABEL_38",
|
53 |
+
"39": "LABEL_39",
|
54 |
+
"40": "LABEL_40",
|
55 |
+
"41": "LABEL_41",
|
56 |
+
"42": "LABEL_42",
|
57 |
+
"43": "LABEL_43",
|
58 |
+
"44": "LABEL_44",
|
59 |
+
"45": "LABEL_45",
|
60 |
+
"46": "LABEL_46",
|
61 |
+
"47": "LABEL_47",
|
62 |
+
"48": "LABEL_48"
|
63 |
+
},
|
64 |
+
"initializer_range": 0.02,
|
65 |
+
"intermediate_size": 4096,
|
66 |
+
"label2id": {
|
67 |
+
"LABEL_0": 0,
|
68 |
+
"LABEL_1": 1,
|
69 |
+
"LABEL_10": 10,
|
70 |
+
"LABEL_11": 11,
|
71 |
+
"LABEL_12": 12,
|
72 |
+
"LABEL_13": 13,
|
73 |
+
"LABEL_14": 14,
|
74 |
+
"LABEL_15": 15,
|
75 |
+
"LABEL_16": 16,
|
76 |
+
"LABEL_17": 17,
|
77 |
+
"LABEL_18": 18,
|
78 |
+
"LABEL_19": 19,
|
79 |
+
"LABEL_2": 2,
|
80 |
+
"LABEL_20": 20,
|
81 |
+
"LABEL_21": 21,
|
82 |
+
"LABEL_22": 22,
|
83 |
+
"LABEL_23": 23,
|
84 |
+
"LABEL_24": 24,
|
85 |
+
"LABEL_25": 25,
|
86 |
+
"LABEL_26": 26,
|
87 |
+
"LABEL_27": 27,
|
88 |
+
"LABEL_28": 28,
|
89 |
+
"LABEL_29": 29,
|
90 |
+
"LABEL_3": 3,
|
91 |
+
"LABEL_30": 30,
|
92 |
+
"LABEL_31": 31,
|
93 |
+
"LABEL_32": 32,
|
94 |
+
"LABEL_33": 33,
|
95 |
+
"LABEL_34": 34,
|
96 |
+
"LABEL_35": 35,
|
97 |
+
"LABEL_36": 36,
|
98 |
+
"LABEL_37": 37,
|
99 |
+
"LABEL_38": 38,
|
100 |
+
"LABEL_39": 39,
|
101 |
+
"LABEL_4": 4,
|
102 |
+
"LABEL_40": 40,
|
103 |
+
"LABEL_41": 41,
|
104 |
+
"LABEL_42": 42,
|
105 |
+
"LABEL_43": 43,
|
106 |
+
"LABEL_44": 44,
|
107 |
+
"LABEL_45": 45,
|
108 |
+
"LABEL_46": 46,
|
109 |
+
"LABEL_47": 47,
|
110 |
+
"LABEL_48": 48,
|
111 |
+
"LABEL_5": 5,
|
112 |
+
"LABEL_6": 6,
|
113 |
+
"LABEL_7": 7,
|
114 |
+
"LABEL_8": 8,
|
115 |
+
"LABEL_9": 9
|
116 |
+
},
|
117 |
+
"layer_norm_eps": 1e-05,
|
118 |
+
"max_position_embeddings": 514,
|
119 |
+
"model_type": "xlm-roberta",
|
120 |
+
"num_attention_heads": 16,
|
121 |
+
"num_hidden_layers": 24,
|
122 |
+
"output_past": true,
|
123 |
+
"pad_token_id": 1,
|
124 |
+
"position_embedding_type": "absolute",
|
125 |
+
"torch_dtype": "float32",
|
126 |
+
"transformers_version": "4.44.2",
|
127 |
+
"type_vocab_size": 1,
|
128 |
+
"use_cache": true,
|
129 |
+
"vocab_size": 250002
|
130 |
+
}
|
model-001.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85cb2fd08f3de93fb1a595a37bcf552bfc88f753bf0334810f771c8ddc620b87
|
3 |
+
size 2235612764
|
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 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
|
3 |
+
size 17082832
|
tokenizer_config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"max_length": 128,
|
50 |
+
"model_max_length": 512,
|
51 |
+
"pad_to_multiple_of": null,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"pad_token_type_id": 0,
|
54 |
+
"padding_side": "right",
|
55 |
+
"sep_token": "</s>",
|
56 |
+
"stride": 0,
|
57 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
58 |
+
"truncation_side": "right",
|
59 |
+
"truncation_strategy": "longest_first",
|
60 |
+
"unk_token": "<unk>"
|
61 |
+
}
|