Upload 6 files
Browse files- added_tokens.json +44 -0
- config.json +26 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"$": 31005,
|
| 3 |
+
"$3.822": 31006,
|
| 4 |
+
"$300": 31007,
|
| 5 |
+
"$4.122": 31008,
|
| 6 |
+
"%": 31028,
|
| 7 |
+
"(10)": 31013,
|
| 8 |
+
"(75%)": 31003,
|
| 9 |
+
"(SGI)": 31032,
|
| 10 |
+
"(cada Periodo dura 4 meses de labores acad茅micas)": 31004,
|
| 11 |
+
"(ordinaria, extraordinaria y especial)": 31037,
|
| 12 |
+
"/": 31031,
|
| 13 |
+
"08H00": 31039,
|
| 14 |
+
"10%": 31009,
|
| 15 |
+
"1160001720001": 31042,
|
| 16 |
+
"15%": 31010,
|
| 17 |
+
"17H00": 31040,
|
| 18 |
+
"25%": 31011,
|
| 19 |
+
"27": 31016,
|
| 20 |
+
"2902548118-AUTOGESTI脫N": 31041,
|
| 21 |
+
"30%": 31023,
|
| 22 |
+
"40%": 31024,
|
| 23 |
+
"50%": 31021,
|
| 24 |
+
"60%": 31025,
|
| 25 |
+
"7": 31035,
|
| 26 |
+
"7.99": 31020,
|
| 27 |
+
"70": 31034,
|
| 28 |
+
"70%": 31022,
|
| 29 |
+
"720": 31012,
|
| 30 |
+
"75": 31029,
|
| 31 |
+
"75%": 31026,
|
| 32 |
+
"8.99": 31019,
|
| 33 |
+
";": 31033,
|
| 34 |
+
"Decano/a": 31018,
|
| 35 |
+
"Director/a": 31017,
|
| 36 |
+
"Software": 31027,
|
| 37 |
+
"decano/a": 31015,
|
| 38 |
+
"https://unl.edu.ec/posgrados": 31038,
|
| 39 |
+
"secuencial/continua": 31002,
|
| 40 |
+
"software": 31036,
|
| 41 |
+
"subdirecci贸n.tesoreria@unl.edu.ec": 31043,
|
| 42 |
+
"y/o": 31030,
|
| 43 |
+
"脫rgano Colegiado Superior": 31014
|
| 44 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "leo123/DistilBERT-Preguntas-Respuestas-Posgrados",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForQuestionAnswering"
|
| 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 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"layer_norm_eps": 1e-12,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "bert",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 12,
|
| 18 |
+
"output_past": true,
|
| 19 |
+
"pad_token_id": 1,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.27.4",
|
| 23 |
+
"type_vocab_size": 2,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 31044
|
| 26 |
+
}
|
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 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_basic_tokenize": true,
|
| 4 |
+
"do_lower_case": false,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"never_split": null,
|
| 8 |
+
"pad_token": "[PAD]",
|
| 9 |
+
"sep_token": "[SEP]",
|
| 10 |
+
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--mrm8488--distill-bert-base-spanish-wwm-cased-finetuned-spa-squad2-es/snapshots/dcadd98e59cd7ce8efd00cb4c61a024e2895b4c1/special_tokens_map.json",
|
| 11 |
+
"strip_accents": null,
|
| 12 |
+
"tokenize_chinese_chars": true,
|
| 13 |
+
"tokenizer_class": "BertTokenizer",
|
| 14 |
+
"unk_token": "[UNK]"
|
| 15 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|