Upload 6 files
Browse files- config.json +63 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "cointegrated/rubert-tiny",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"emb_size": 312,
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 312,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "PLAIN",
|
| 15 |
+
"1": "VERBATIM",
|
| 16 |
+
"2": "CARDINAL",
|
| 17 |
+
"3": "TIME",
|
| 18 |
+
"4": "FRACTION",
|
| 19 |
+
"5": "LETTERS",
|
| 20 |
+
"6": "DIGIT",
|
| 21 |
+
"7": "MONEY",
|
| 22 |
+
"8": "TELEPHONE",
|
| 23 |
+
"9": "ORDINAL",
|
| 24 |
+
"10": "ELECTRONIC",
|
| 25 |
+
"11": "DECIMAL",
|
| 26 |
+
"12": "MEASURE",
|
| 27 |
+
"13": "DATE",
|
| 28 |
+
"14": "ABBREVIATION",
|
| 29 |
+
"15": "ADRESS"
|
| 30 |
+
},
|
| 31 |
+
"initializer_range": 0.02,
|
| 32 |
+
"intermediate_size": 600,
|
| 33 |
+
"label2id": {
|
| 34 |
+
"ABBREVIATION": 14,
|
| 35 |
+
"ADRESS": 15,
|
| 36 |
+
"CARDINAL": 2,
|
| 37 |
+
"DATE": 13,
|
| 38 |
+
"DECIMAL": 11,
|
| 39 |
+
"DIGIT": 6,
|
| 40 |
+
"ELECTRONIC": 10,
|
| 41 |
+
"FRACTION": 4,
|
| 42 |
+
"LETTERS": 5,
|
| 43 |
+
"MEASURE": 12,
|
| 44 |
+
"MONEY": 7,
|
| 45 |
+
"ORDINAL": 9,
|
| 46 |
+
"PLAIN": 0,
|
| 47 |
+
"TELEPHONE": 8,
|
| 48 |
+
"TIME": 3,
|
| 49 |
+
"VERBATIM": 1
|
| 50 |
+
},
|
| 51 |
+
"layer_norm_eps": 1e-12,
|
| 52 |
+
"max_position_embeddings": 512,
|
| 53 |
+
"model_type": "bert",
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_hidden_layers": 3,
|
| 56 |
+
"pad_token_id": 0,
|
| 57 |
+
"position_embedding_type": "absolute",
|
| 58 |
+
"torch_dtype": "float32",
|
| 59 |
+
"transformers_version": "4.28.1",
|
| 60 |
+
"type_vocab_size": 2,
|
| 61 |
+
"use_cache": true,
|
| 62 |
+
"vocab_size": 29564
|
| 63 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e636f33b833a1e4e1c090ea2d7e0253288a86c4fff54c8b4d879ef7bb1b1ce0e
|
| 3 |
+
size 46787865
|
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 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_basic_tokenize": true,
|
| 5 |
+
"do_lower_case": false,
|
| 6 |
+
"mask_token": "[MASK]",
|
| 7 |
+
"model_max_length": 512,
|
| 8 |
+
"never_split": null,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 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
|
|
|