Commit
·
dda349b
1
Parent(s):
eaf1c7a
Update model with new ner mapping
Browse files- .DS_Store +0 -0
- config.json +46 -3
- onnx/model.onnx +1 -1
- onnx/model_quantized.onnx +1 -1
- quantize_config.json +33 -3
- special_tokens_map.json +7 -3
- tokenizer.json +0 -0
- tokenizer_config.json +59 -3
- vocab.txt +0 -0
.DS_Store
ADDED
|
Binary file (6.15 kB). View file
|
|
|
config.json
CHANGED
|
@@ -1,3 +1,46 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-NER-conll2003",
|
| 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": "O",
|
| 13 |
+
"1": "B-PER",
|
| 14 |
+
"2": "I-PER",
|
| 15 |
+
"3": "B-ORG",
|
| 16 |
+
"4": "I-ORG",
|
| 17 |
+
"5": "B-LOC",
|
| 18 |
+
"6": "I-LOC",
|
| 19 |
+
"7": "B-MISC",
|
| 20 |
+
"8": "I-MISC"
|
| 21 |
+
},
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"B-LOC": 5,
|
| 25 |
+
"B-MISC": 7,
|
| 26 |
+
"B-ORG": 3,
|
| 27 |
+
"B-PER": 1,
|
| 28 |
+
"I-LOC": 6,
|
| 29 |
+
"I-MISC": 8,
|
| 30 |
+
"I-ORG": 4,
|
| 31 |
+
"I-PER": 2,
|
| 32 |
+
"O": 0
|
| 33 |
+
},
|
| 34 |
+
"max_position_embeddings": 512,
|
| 35 |
+
"model_type": "distilbert",
|
| 36 |
+
"n_heads": 12,
|
| 37 |
+
"n_layers": 6,
|
| 38 |
+
"output_past": true,
|
| 39 |
+
"pad_token_id": 0,
|
| 40 |
+
"qa_dropout": 0.1,
|
| 41 |
+
"seq_classif_dropout": 0.2,
|
| 42 |
+
"sinusoidal_pos_embds": false,
|
| 43 |
+
"tie_weights_": true,
|
| 44 |
+
"transformers_version": "4.33.2",
|
| 45 |
+
"vocab_size": 28996
|
| 46 |
+
}
|
onnx/model.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 260926485
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6713b6cd461eb50b278f93a69e78236b7c76c38eb9bdd8ca33f7c2016a9dc5a
|
| 3 |
size 260926485
|
onnx/model_quantized.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 65816665
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ef50677f505b126dd13c405bf5a5003af0a4c9ba6fa7eab8b92d05cbd4d725e
|
| 3 |
size 65816665
|
quantize_config.json
CHANGED
|
@@ -1,3 +1,33 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"per_channel": true,
|
| 3 |
+
"reduce_range": true,
|
| 4 |
+
"per_model_config": {
|
| 5 |
+
"model": {
|
| 6 |
+
"op_types": [
|
| 7 |
+
"Sqrt",
|
| 8 |
+
"Shape",
|
| 9 |
+
"ReduceMean",
|
| 10 |
+
"Concat",
|
| 11 |
+
"Transpose",
|
| 12 |
+
"Add",
|
| 13 |
+
"Slice",
|
| 14 |
+
"Erf",
|
| 15 |
+
"Expand",
|
| 16 |
+
"Reshape",
|
| 17 |
+
"Unsqueeze",
|
| 18 |
+
"Sub",
|
| 19 |
+
"Softmax",
|
| 20 |
+
"Mul",
|
| 21 |
+
"Div",
|
| 22 |
+
"Cast",
|
| 23 |
+
"Equal",
|
| 24 |
+
"Pow",
|
| 25 |
+
"Where",
|
| 26 |
+
"MatMul",
|
| 27 |
+
"Constant",
|
| 28 |
+
"Gather"
|
| 29 |
+
],
|
| 30 |
+
"weight_type": "QInt8"
|
| 31 |
+
}
|
| 32 |
+
}
|
| 33 |
+
}
|
special_tokens_map.json
CHANGED
|
@@ -1,3 +1,7 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,3 +1,59 @@
|
|
| 1 |
-
|
| 2 |
-
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": false,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"max_length": 512,
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"stride": 0,
|
| 53 |
+
"strip_accents": null,
|
| 54 |
+
"tokenize_chinese_chars": true,
|
| 55 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 56 |
+
"truncation_side": "right",
|
| 57 |
+
"truncation_strategy": "longest_first",
|
| 58 |
+
"unk_token": "[UNK]"
|
| 59 |
+
}
|
vocab.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|