Upload 6 files
Browse files- config.json +130 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "HooshvareLab/bert-base-parsbert-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "\u0627\u0633\u062a\u0627\u0631\u062a\u0627\u067e",
|
| 13 |
+
"1": "\u0627\u0642\u062a\u0635\u0627\u062f",
|
| 14 |
+
"2": "\u0627\u0645\u0646\u06cc\u062a \u0633\u0627\u06cc\u0628\u0631\u06cc",
|
| 15 |
+
"3": "\u0627\u06cc\u0646\u062a\u0631\u0646\u062a \u0627\u0634\u06cc\u0627",
|
| 16 |
+
"4": "\u0628\u0627\u0632\u0627\u0631\u06cc\u0627\u0628\u06cc",
|
| 17 |
+
"5": "\u0628\u0627\u0632\u06cc \u0631\u0627\u06cc\u0627\u0646\u0647 \u0627\u06cc",
|
| 18 |
+
"6": "\u0628\u0631\u0646\u0627\u0645\u0647 \u0646\u0648\u06cc\u0633\u06cc",
|
| 19 |
+
"7": "\u0628\u0644\u0627\u06a9 \u0686\u06cc\u0646",
|
| 20 |
+
"8": "\u0628\u0647\u0631\u0647 \u0648\u0631\u06cc",
|
| 21 |
+
"9": "\u062a\u0627\u0631\u06cc\u062e",
|
| 22 |
+
"10": "\u062a\u062c\u0631\u0628\u0647 \u06a9\u0627\u0631\u0628\u0631\u06cc",
|
| 23 |
+
"11": "\u062a\u062d\u0635\u06cc\u0644\u06cc \u0648 \u0622\u0645\u0648\u0632\u0634\u06cc",
|
| 24 |
+
"12": "\u062d\u0642\u0648\u0642\u06cc",
|
| 25 |
+
"13": "\u062e\u0627\u0646\u0648\u0627\u062f\u0647",
|
| 26 |
+
"14": "\u062e\u0648\u062f\u0634\u0646\u0627\u0633\u06cc",
|
| 27 |
+
"15": "\u062f\u0627\u0633\u062a\u0627\u0646",
|
| 28 |
+
"16": "\u0631\u0627\u0628\u0637\u0647",
|
| 29 |
+
"17": "\u0631\u0648\u0627\u0646\u0634\u0646\u0627\u0633\u06cc",
|
| 30 |
+
"18": "\u0632\u0646\u0627\u0646",
|
| 31 |
+
"19": "\u0633\u0641\u0631",
|
| 32 |
+
"20": "\u0633\u0644\u0627\u0645\u062a",
|
| 33 |
+
"21": "\u0633\u0644\u0627\u0645\u062a \u0631\u0648\u0627\u0646\u06cc",
|
| 34 |
+
"22": "\u0633\u06cc\u0627\u0633\u062a",
|
| 35 |
+
"23": "\u0634\u0628\u06a9\u0647 \u0627\u062c\u062a\u0645\u0627\u0639\u06cc",
|
| 36 |
+
"24": "\u0634\u063a\u0644 \u0648 \u06a9\u0627\u0631",
|
| 37 |
+
"25": "\u0637\u0631\u0627\u062d\u06cc \u062f\u06cc\u062c\u06cc\u062a\u0627\u0644",
|
| 38 |
+
"26": "\u0639\u0644\u0648\u0645",
|
| 39 |
+
"27": "\u0639\u06a9\u0627\u0633\u06cc",
|
| 40 |
+
"28": "\u063a\u0630\u0627",
|
| 41 |
+
"29": "\u0641\u0631\u0647\u0646\u06af",
|
| 42 |
+
"30": "\u0641\u0631\u06cc\u0644\u0646\u0633\u0631\u06cc",
|
| 43 |
+
"31": "\u0641\u0644\u0633\u0641\u0647",
|
| 44 |
+
"32": "\u0641\u06cc\u0644\u0645 \u0648 \u0633\u06cc\u0646\u0645\u0627",
|
| 45 |
+
"33": "\u0641\u06cc\u0646 \u062a\u06a9",
|
| 46 |
+
"34": "\u0645\u062d\u06cc\u0637 \u0632\u06cc\u0633\u062a",
|
| 47 |
+
"35": "\u0645\u0630\u0647\u0628\u06cc",
|
| 48 |
+
"36": "\u0645\u0647\u0627\u062c\u0631\u062a",
|
| 49 |
+
"37": "\u0645\u0647\u0646\u062f\u0633\u06cc \u0646\u0631\u0645 \u0627\u0641\u0632\u0627\u0631",
|
| 50 |
+
"38": "\u0645\u0648\u0633\u06cc\u0642\u06cc",
|
| 51 |
+
"39": "\u0645\u0648\u0641\u0642\u06cc\u062a",
|
| 52 |
+
"40": "\u0646\u0648\u06cc\u0633\u0646\u062f\u06af\u06cc",
|
| 53 |
+
"41": "\u0647\u0646\u0631",
|
| 54 |
+
"42": "\u0647\u0648\u0627 \u0641\u0636\u0627",
|
| 55 |
+
"43": "\u0647\u0648\u0634 \u0645\u0635\u0646\u0648\u0639\u06cc",
|
| 56 |
+
"44": "\u0648\u0631\u0632\u0634\u06cc",
|
| 57 |
+
"45": "\u067e\u0627\u062f\u06a9\u0633\u062a",
|
| 58 |
+
"46": "\u067e\u0648\u0644 \u0631\u0645\u0632\u06cc",
|
| 59 |
+
"47": "\u06a9\u0627\u0631\u0622\u0641\u0631\u06cc\u0646\u06cc",
|
| 60 |
+
"48": "\u06a9\u062a\u0627\u0628",
|
| 61 |
+
"49": "\u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0645\u0627\u0634\u06cc\u0646"
|
| 62 |
+
},
|
| 63 |
+
"initializer_range": 0.02,
|
| 64 |
+
"intermediate_size": 3072,
|
| 65 |
+
"label2id": {
|
| 66 |
+
"\u0627\u0633\u062a\u0627\u0631\u062a\u0627\u067e": 0,
|
| 67 |
+
"\u0627\u0642\u062a\u0635\u0627\u062f": 1,
|
| 68 |
+
"\u0627\u0645\u0646\u06cc\u062a \u0633\u0627\u06cc\u0628\u0631\u06cc": 2,
|
| 69 |
+
"\u0627\u06cc\u0646\u062a\u0631\u0646\u062a \u0627\u0634\u06cc\u0627": 3,
|
| 70 |
+
"\u0628\u0627\u0632\u0627\u0631\u06cc\u0627\u0628\u06cc": 4,
|
| 71 |
+
"\u0628\u0627\u0632\u06cc \u0631\u0627\u06cc\u0627\u0646\u0647 \u0627\u06cc": 5,
|
| 72 |
+
"\u0628\u0631\u0646\u0627\u0645\u0647 \u0646\u0648\u06cc\u0633\u06cc": 6,
|
| 73 |
+
"\u0628\u0644\u0627\u06a9 \u0686\u06cc\u0646": 7,
|
| 74 |
+
"\u0628\u0647\u0631\u0647 \u0648\u0631\u06cc": 8,
|
| 75 |
+
"\u062a\u0627\u0631\u06cc\u062e": 9,
|
| 76 |
+
"\u062a\u062c\u0631\u0628\u0647 \u06a9\u0627\u0631\u0628\u0631\u06cc": 10,
|
| 77 |
+
"\u062a\u062d\u0635\u06cc\u0644\u06cc \u0648 \u0622\u0645\u0648\u0632\u0634\u06cc": 11,
|
| 78 |
+
"\u062d\u0642\u0648\u0642\u06cc": 12,
|
| 79 |
+
"\u062e\u0627\u0646\u0648\u0627\u062f\u0647": 13,
|
| 80 |
+
"\u062e\u0648\u062f\u0634\u0646\u0627\u0633\u06cc": 14,
|
| 81 |
+
"\u062f\u0627\u0633\u062a\u0627\u0646": 15,
|
| 82 |
+
"\u0631\u0627\u0628\u0637\u0647": 16,
|
| 83 |
+
"\u0631\u0648\u0627\u0646\u0634\u0646\u0627\u0633\u06cc": 17,
|
| 84 |
+
"\u0632\u0646\u0627\u0646": 18,
|
| 85 |
+
"\u0633\u0641\u0631": 19,
|
| 86 |
+
"\u0633\u0644\u0627\u0645\u062a": 20,
|
| 87 |
+
"\u0633\u0644\u0627\u0645\u062a \u0631\u0648\u0627\u0646\u06cc": 21,
|
| 88 |
+
"\u0633\u06cc\u0627\u0633\u062a": 22,
|
| 89 |
+
"\u0634\u0628\u06a9\u0647 \u0627\u062c\u062a\u0645\u0627\u0639\u06cc": 23,
|
| 90 |
+
"\u0634\u063a\u0644 \u0648 \u06a9\u0627\u0631": 24,
|
| 91 |
+
"\u0637\u0631\u0627\u062d\u06cc \u062f\u06cc\u062c\u06cc\u062a\u0627\u0644": 25,
|
| 92 |
+
"\u0639\u0644\u0648\u0645": 26,
|
| 93 |
+
"\u0639\u06a9\u0627\u0633\u06cc": 27,
|
| 94 |
+
"\u063a\u0630\u0627": 28,
|
| 95 |
+
"\u0641\u0631\u0647\u0646\u06af": 29,
|
| 96 |
+
"\u0641\u0631\u06cc\u0644\u0646\u0633\u0631\u06cc": 30,
|
| 97 |
+
"\u0641\u0644\u0633\u0641\u0647": 31,
|
| 98 |
+
"\u0641\u06cc\u0644\u0645 \u0648 \u0633\u06cc\u0646\u0645\u0627": 32,
|
| 99 |
+
"\u0641\u06cc\u0646 \u062a\u06a9": 33,
|
| 100 |
+
"\u0645\u062d\u06cc\u0637 \u0632\u06cc\u0633\u062a": 34,
|
| 101 |
+
"\u0645\u0630\u0647\u0628\u06cc": 35,
|
| 102 |
+
"\u0645\u0647\u0627\u062c\u0631\u062a": 36,
|
| 103 |
+
"\u0645\u0647\u0646\u062f\u0633\u06cc \u0646\u0631\u0645 \u0627\u0641\u0632\u0627\u0631": 37,
|
| 104 |
+
"\u0645\u0648\u0633\u06cc\u0642\u06cc": 38,
|
| 105 |
+
"\u0645\u0648\u0641\u0642\u06cc\u062a": 39,
|
| 106 |
+
"\u0646\u0648\u06cc\u0633\u0646\u062f\u06af\u06cc": 40,
|
| 107 |
+
"\u0647\u0646\u0631": 41,
|
| 108 |
+
"\u0647\u0648\u0627 \u0641\u0636\u0627": 42,
|
| 109 |
+
"\u0647\u0648\u0634 \u0645\u0635\u0646\u0648\u0639\u06cc": 43,
|
| 110 |
+
"\u0648\u0631\u0632\u0634\u06cc": 44,
|
| 111 |
+
"\u067e\u0627\u062f\u06a9\u0633\u062a": 45,
|
| 112 |
+
"\u067e\u0648\u0644 \u0631\u0645\u0632\u06cc": 46,
|
| 113 |
+
"\u06a9\u0627\u0631\u0622\u0641\u0631\u06cc\u0646\u06cc": 47,
|
| 114 |
+
"\u06a9\u062a\u0627\u0628": 48,
|
| 115 |
+
"\u06cc\u0627\u062f\u06af\u06cc\u0631\u06cc \u0645\u0627\u0634\u06cc\u0646": 49
|
| 116 |
+
},
|
| 117 |
+
"layer_norm_eps": 1e-12,
|
| 118 |
+
"max_position_embeddings": 512,
|
| 119 |
+
"model_type": "bert",
|
| 120 |
+
"num_attention_heads": 12,
|
| 121 |
+
"num_hidden_layers": 12,
|
| 122 |
+
"pad_token_id": 0,
|
| 123 |
+
"position_embedding_type": "absolute",
|
| 124 |
+
"problem_type": "single_label_classification",
|
| 125 |
+
"torch_dtype": "float32",
|
| 126 |
+
"transformers_version": "4.41.2",
|
| 127 |
+
"type_vocab_size": 2,
|
| 128 |
+
"use_cache": true,
|
| 129 |
+
"vocab_size": 100000
|
| 130 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[MASK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[SEP]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"max_length": 512,
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c16cd744a4ea8e15172e5821439db4debdb91476c0db76bea87df371e7e58187
|
| 3 |
+
size 5048
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|