Initial Commit
Browse files- config.json +61 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"hidden_dim": 3072,
|
| 10 |
+
"id2label": {
|
| 11 |
+
"0": "O",
|
| 12 |
+
"1": "B-Amenity",
|
| 13 |
+
"2": "I-Amenity",
|
| 14 |
+
"3": "B-Dish",
|
| 15 |
+
"4": "I-Dish",
|
| 16 |
+
"5": "B-Rating",
|
| 17 |
+
"6": "I-Rating",
|
| 18 |
+
"7": "B-Restaurant_Name",
|
| 19 |
+
"8": "I-Restaurant_Name",
|
| 20 |
+
"9": "B-Hours",
|
| 21 |
+
"10": "I-Hours",
|
| 22 |
+
"11": "B-Location",
|
| 23 |
+
"12": "I-Location",
|
| 24 |
+
"13": "B-Price",
|
| 25 |
+
"14": "I-Price",
|
| 26 |
+
"15": "B-Cuisine",
|
| 27 |
+
"16": "I-Cuisine"
|
| 28 |
+
},
|
| 29 |
+
"initializer_range": 0.02,
|
| 30 |
+
"label2id": {
|
| 31 |
+
"B-Amenity": 1,
|
| 32 |
+
"B-Cuisine": 15,
|
| 33 |
+
"B-Dish": 3,
|
| 34 |
+
"B-Hours": 9,
|
| 35 |
+
"B-Location": 11,
|
| 36 |
+
"B-Price": 13,
|
| 37 |
+
"B-Rating": 5,
|
| 38 |
+
"B-Restaurant_Name": 7,
|
| 39 |
+
"I-Amenity": 2,
|
| 40 |
+
"I-Cuisine": 16,
|
| 41 |
+
"I-Dish": 4,
|
| 42 |
+
"I-Hours": 10,
|
| 43 |
+
"I-Location": 12,
|
| 44 |
+
"I-Price": 14,
|
| 45 |
+
"I-Rating": 6,
|
| 46 |
+
"I-Restaurant_Name": 8,
|
| 47 |
+
"O": 0
|
| 48 |
+
},
|
| 49 |
+
"max_position_embeddings": 512,
|
| 50 |
+
"model_type": "distilbert",
|
| 51 |
+
"n_heads": 12,
|
| 52 |
+
"n_layers": 6,
|
| 53 |
+
"pad_token_id": 0,
|
| 54 |
+
"qa_dropout": 0.1,
|
| 55 |
+
"seq_classif_dropout": 0.2,
|
| 56 |
+
"sinusoidal_pos_embds": false,
|
| 57 |
+
"tie_weights_": true,
|
| 58 |
+
"torch_dtype": "float32",
|
| 59 |
+
"transformers_version": "4.51.3",
|
| 60 |
+
"vocab_size": 30522
|
| 61 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14e51a629ab0a61a9c1b903babc03545cb2cc9a59c2bf9f829fc812487c5bbae
|
| 3 |
+
size 265537698
|
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": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6195362ac3e6fbc806bb8c9651d322c921ee5c34f47a9deb4bf66324d4a701aa
|
| 3 |
+
size 5240
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|