AbidHasan95
commited on
Commit
•
1455e81
1
Parent(s):
2a8e9a7
First commit
Browse files- config.json +36 -0
- model.safetensors +3 -0
- sms_classifier.py +61 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "abc2",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"custom_pipelines": {
|
9 |
+
"sms-classification": {
|
10 |
+
"impl": "sms_classifier.SMSClassificationPipeline",
|
11 |
+
"pt": [
|
12 |
+
"AutoModelForSequenceClassification"
|
13 |
+
],
|
14 |
+
"tf": [
|
15 |
+
"TFAutoModelForSequenceClassification"
|
16 |
+
]
|
17 |
+
}
|
18 |
+
},
|
19 |
+
"hidden_act": "gelu",
|
20 |
+
"hidden_dropout_prob": 0.1,
|
21 |
+
"hidden_size": 512,
|
22 |
+
"initializer_range": 0.02,
|
23 |
+
"intermediate_size": 2048,
|
24 |
+
"layer_norm_eps": 1e-12,
|
25 |
+
"max_position_embeddings": 512,
|
26 |
+
"model_type": "bert",
|
27 |
+
"num_attention_heads": 8,
|
28 |
+
"num_hidden_layers": 2,
|
29 |
+
"pad_token_id": 0,
|
30 |
+
"position_embedding_type": "absolute",
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.38.2",
|
33 |
+
"type_vocab_size": 2,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 30522
|
36 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fa25d6948b403ef3438761d39e0e66ac075bb066d75f866041b597067476d77
|
3 |
+
size 89844232
|
sms_classifier.py
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
from transformers import pipeline, BertModel, AutoTokenizer, PretrainedConfig,PreTrainedModel, Pipeline
|
2 |
+
|
3 |
+
|
4 |
+
class SMSClassificationPipeline(Pipeline):
|
5 |
+
def _sanitize_parameters(self, **kwargs):
|
6 |
+
preprocess_kwargs = {}
|
7 |
+
# if "second_text" in kwargs:
|
8 |
+
# preprocess_kwargs["second_text"] = kwargs["second_text"]
|
9 |
+
return preprocess_kwargs, {}, {}
|
10 |
+
|
11 |
+
def preprocess(self, text):
|
12 |
+
return self.tokenizer(text, return_tensors=self.framework)
|
13 |
+
|
14 |
+
def _forward(self, model_inputs):
|
15 |
+
return self.model(**model_inputs)
|
16 |
+
|
17 |
+
def postprocess(self, model_outputs):
|
18 |
+
seq_labels = [
|
19 |
+
"Transaction",
|
20 |
+
"Courier",
|
21 |
+
"OTP",
|
22 |
+
"Expiry",
|
23 |
+
"Misc",
|
24 |
+
"Tele Marketing",
|
25 |
+
"Spam",
|
26 |
+
]
|
27 |
+
|
28 |
+
token_class_labels = [
|
29 |
+
'O',
|
30 |
+
'Courier Service',
|
31 |
+
'Credit',
|
32 |
+
'Date',
|
33 |
+
'Debit',
|
34 |
+
'Email',
|
35 |
+
'Expiry',
|
36 |
+
'Item',
|
37 |
+
'Order ID',
|
38 |
+
'Organization',
|
39 |
+
'OTP',
|
40 |
+
'Phone Number',
|
41 |
+
'Refund',
|
42 |
+
'Time',
|
43 |
+
'Tracking ID',
|
44 |
+
'URL',
|
45 |
+
]
|
46 |
+
# logits = model_outputs.logits[0].numpy()
|
47 |
+
# probabilities = softmax(logits)
|
48 |
+
|
49 |
+
# best_class = np.argmax(probabilities)
|
50 |
+
# label = self.model.config.id2label[best_class]
|
51 |
+
# score = probabilities[best_class].item()
|
52 |
+
# logits = logits.tolist()
|
53 |
+
# return {"label": label, "score": score, "logits": logits}
|
54 |
+
# out = self.tokenizer(model_outputs, return_tensors="pt")
|
55 |
+
token_classification_logits, sequence_logits = model_outputs
|
56 |
+
token_classification_logits = token_classification_logits.argmax(2)[0]
|
57 |
+
sequence_logits = sequence_logits.argmax(1)[0]
|
58 |
+
token_classification_out = [token_class_labels[i] for i in token_classification_logits.tolist()]
|
59 |
+
seq_classification_out = seq_labels[sequence_logits]
|
60 |
+
# return token_classification_out, seq_classification_out
|
61 |
+
return {"token_classfier":token_classification_out, "sequence_classfier": seq_classification_out}
|
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 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|