Init
Browse files- config.json +74 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +13 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-re-punctuate",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForTokenClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "UPPER_",
|
| 13 |
+
"1": "Upper_",
|
| 14 |
+
"2": "lower_",
|
| 15 |
+
"3": "UPPER.",
|
| 16 |
+
"4": "Upper.",
|
| 17 |
+
"5": "lower.",
|
| 18 |
+
"6": "UPPER,",
|
| 19 |
+
"7": "Upper,",
|
| 20 |
+
"8": "lower,",
|
| 21 |
+
"9": "UPPER!",
|
| 22 |
+
"10": "Upper!",
|
| 23 |
+
"11": "lower!",
|
| 24 |
+
"12": "UPPER?",
|
| 25 |
+
"13": "Upper?",
|
| 26 |
+
"14": "lower?",
|
| 27 |
+
"15": "UPPER:",
|
| 28 |
+
"16": "Upper:",
|
| 29 |
+
"17": "lower:",
|
| 30 |
+
"18": "UPPER;",
|
| 31 |
+
"19": "Upper;",
|
| 32 |
+
"20": "lower;UPPER-",
|
| 33 |
+
"21": "Upper-",
|
| 34 |
+
"22": "lower-"
|
| 35 |
+
},
|
| 36 |
+
"initializer_range": 0.02,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"UPPER!": 9,
|
| 39 |
+
"UPPER,": 6,
|
| 40 |
+
"UPPER.": 3,
|
| 41 |
+
"UPPER:": 15,
|
| 42 |
+
"UPPER;": 18,
|
| 43 |
+
"UPPER?": 12,
|
| 44 |
+
"UPPER_": 0,
|
| 45 |
+
"Upper!": 10,
|
| 46 |
+
"Upper,": 7,
|
| 47 |
+
"Upper-": 21,
|
| 48 |
+
"Upper.": 4,
|
| 49 |
+
"Upper:": 16,
|
| 50 |
+
"Upper;": 19,
|
| 51 |
+
"Upper?": 13,
|
| 52 |
+
"Upper_": 1,
|
| 53 |
+
"lower!": 11,
|
| 54 |
+
"lower,": 8,
|
| 55 |
+
"lower-": 22,
|
| 56 |
+
"lower.": 5,
|
| 57 |
+
"lower:": 17,
|
| 58 |
+
"lower;UPPER-": 20,
|
| 59 |
+
"lower?": 14,
|
| 60 |
+
"lower_": 2
|
| 61 |
+
},
|
| 62 |
+
"max_position_embeddings": 512,
|
| 63 |
+
"model_type": "distilbert",
|
| 64 |
+
"n_heads": 12,
|
| 65 |
+
"n_layers": 6,
|
| 66 |
+
"pad_token_id": 0,
|
| 67 |
+
"qa_dropout": 0.1,
|
| 68 |
+
"seq_classif_dropout": 0.2,
|
| 69 |
+
"sinusoidal_pos_embds": false,
|
| 70 |
+
"tie_weights_": true,
|
| 71 |
+
"torch_dtype": "float32",
|
| 72 |
+
"transformers_version": "4.27.4",
|
| 73 |
+
"vocab_size": 30522
|
| 74 |
+
}
|
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 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_lower_case": true,
|
| 4 |
+
"mask_token": "[MASK]",
|
| 5 |
+
"model_max_length": 512,
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"special_tokens_map_file": null,
|
| 9 |
+
"strip_accents": null,
|
| 10 |
+
"tokenize_chinese_chars": true,
|
| 11 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 12 |
+
"unk_token": "[UNK]"
|
| 13 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3821eb71ffec3cb3f38966b58ac10a102de3c75452f804546b254e6d68c33b39
|
| 3 |
+
size 3515
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|