Upload folder using huggingface_hub
Browse files- label_mappings.json +76 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
- training_config.json +12 -0
- vocab.txt +0 -0
label_mappings.json
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tag2id": {
|
| 3 |
+
"B-amount": 0,
|
| 4 |
+
"B-date": 1,
|
| 5 |
+
"B-description": 2,
|
| 6 |
+
"B-indicator_amount": 3,
|
| 7 |
+
"B-indicator_date": 4,
|
| 8 |
+
"B-indicator_description": 5,
|
| 9 |
+
"B-indicator_receiver_hr": 6,
|
| 10 |
+
"B-indicator_receiver_inn": 7,
|
| 11 |
+
"B-indicator_receiver_name": 8,
|
| 12 |
+
"B-indicator_transaction_code": 9,
|
| 13 |
+
"B-receiver_hr": 10,
|
| 14 |
+
"B-receiver_inn": 11,
|
| 15 |
+
"B-receiver_name": 12,
|
| 16 |
+
"B-transaction_code": 13,
|
| 17 |
+
"I-amount": 14,
|
| 18 |
+
"I-description": 15,
|
| 19 |
+
"I-indicator_amount": 16,
|
| 20 |
+
"I-indicator_date": 17,
|
| 21 |
+
"I-indicator_description": 18,
|
| 22 |
+
"I-indicator_receiver_hr": 19,
|
| 23 |
+
"I-indicator_receiver_inn": 20,
|
| 24 |
+
"I-indicator_receiver_name": 21,
|
| 25 |
+
"I-indicator_transaction_code": 22,
|
| 26 |
+
"I-receiver_name": 23,
|
| 27 |
+
"O": 24
|
| 28 |
+
},
|
| 29 |
+
"id2tag": {
|
| 30 |
+
"0": "B-amount",
|
| 31 |
+
"1": "B-date",
|
| 32 |
+
"2": "B-description",
|
| 33 |
+
"3": "B-indicator_amount",
|
| 34 |
+
"4": "B-indicator_date",
|
| 35 |
+
"5": "B-indicator_description",
|
| 36 |
+
"6": "B-indicator_receiver_hr",
|
| 37 |
+
"7": "B-indicator_receiver_inn",
|
| 38 |
+
"8": "B-indicator_receiver_name",
|
| 39 |
+
"9": "B-indicator_transaction_code",
|
| 40 |
+
"10": "B-receiver_hr",
|
| 41 |
+
"11": "B-receiver_inn",
|
| 42 |
+
"12": "B-receiver_name",
|
| 43 |
+
"13": "B-transaction_code",
|
| 44 |
+
"14": "I-amount",
|
| 45 |
+
"15": "I-description",
|
| 46 |
+
"16": "I-indicator_amount",
|
| 47 |
+
"17": "I-indicator_date",
|
| 48 |
+
"18": "I-indicator_description",
|
| 49 |
+
"19": "I-indicator_receiver_hr",
|
| 50 |
+
"20": "I-indicator_receiver_inn",
|
| 51 |
+
"21": "I-indicator_receiver_name",
|
| 52 |
+
"22": "I-indicator_transaction_code",
|
| 53 |
+
"23": "I-receiver_name",
|
| 54 |
+
"24": "O"
|
| 55 |
+
},
|
| 56 |
+
"intent2id": {
|
| 57 |
+
"create_transaction": 0
|
| 58 |
+
},
|
| 59 |
+
"id2intent": {
|
| 60 |
+
"0": "create_transaction"
|
| 61 |
+
},
|
| 62 |
+
"lang2id": {
|
| 63 |
+
"en": 0,
|
| 64 |
+
"mixed": 1,
|
| 65 |
+
"ru": 2,
|
| 66 |
+
"uz_cyrl": 3,
|
| 67 |
+
"uz_latn": 4
|
| 68 |
+
},
|
| 69 |
+
"id2lang": {
|
| 70 |
+
"0": "en",
|
| 71 |
+
"1": "mixed",
|
| 72 |
+
"2": "ru",
|
| 73 |
+
"3": "uz_cyrl",
|
| 74 |
+
"4": "uz_latn"
|
| 75 |
+
}
|
| 76 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a2b3b9bdeae2492d396b1ab6c50873ab8ec1c35294ae89525b935bffcc904bc
|
| 3 |
+
size 671307516
|
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 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "BertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91b56ea529dc82b6f5c780abb1941f688bd147268d902b7ef28b6b6763fe6c41
|
| 3 |
+
size 5777
|
training_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_name": "google-bert/bert-base-multilingual-uncased",
|
| 3 |
+
"num_train_samples": 188336,
|
| 4 |
+
"num_val_samples": 23542,
|
| 5 |
+
"num_test_samples": 23543,
|
| 6 |
+
"num_epochs": 5,
|
| 7 |
+
"batch_size": 32,
|
| 8 |
+
"ner_f1": 0.9996063934364621,
|
| 9 |
+
"intent_f1": 1.0,
|
| 10 |
+
"lang_accuracy": 0.8373189483073525,
|
| 11 |
+
"avg_f1": 0.999803196718231
|
| 12 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|