First commit

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "abc2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "custom_pipelines": {
+    "sms-classification": {
+      "impl": "sms_classifier.SMSClassificationPipeline",
+      "pt": [
+        "AutoModelForSequenceClassification"
+      ],
+      "tf": [
+        "TFAutoModelForSequenceClassification"
+      ]
+    }
+  },
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fa25d6948b403ef3438761d39e0e66ac075bb066d75f866041b597067476d77
+size 89844232

sms_classifier.py

@@ -0,0 +1,61 @@
+from transformers import pipeline, BertModel, AutoTokenizer, PretrainedConfig,PreTrainedModel, Pipeline
+
+
+class SMSClassificationPipeline(Pipeline):
+    def _sanitize_parameters(self, **kwargs):
+        preprocess_kwargs = {}
+        # if "second_text" in kwargs:
+        #     preprocess_kwargs["second_text"] = kwargs["second_text"]
+        return preprocess_kwargs, {}, {}
+
+    def preprocess(self, text):
+        return self.tokenizer(text, return_tensors=self.framework)
+
+    def _forward(self, model_inputs):
+        return self.model(**model_inputs)
+
+    def postprocess(self, model_outputs):
+        seq_labels = [
+            "Transaction",
+            "Courier",
+            "OTP",
+            "Expiry",
+            "Misc",
+            "Tele Marketing",
+            "Spam",
+        ]
+
+        token_class_labels = [
+            'O',
+            'Courier Service',
+            'Credit',
+            'Date',
+            'Debit',
+            'Email',
+            'Expiry',
+            'Item',
+            'Order ID',
+            'Organization',
+            'OTP',
+            'Phone Number',
+            'Refund',
+            'Time',
+            'Tracking ID',
+            'URL',
+        ]
+    #     logits = model_outputs.logits[0].numpy()
+    #     probabilities = softmax(logits)
+
+    #     best_class = np.argmax(probabilities)
+    #     label = self.model.config.id2label[best_class]
+    #     score = probabilities[best_class].item()
+    #     logits = logits.tolist()
+    #     return {"label": label, "score": score, "logits": logits}
+        # out = self.tokenizer(model_outputs, return_tensors="pt")
+        token_classification_logits, sequence_logits  = model_outputs
+        token_classification_logits = token_classification_logits.argmax(2)[0]
+        sequence_logits = sequence_logits.argmax(1)[0]
+        token_classification_out = [token_class_labels[i] for i in token_classification_logits.tolist()]
+        seq_classification_out = seq_labels[sequence_logits]
+        # return token_classification_out, seq_classification_out
+        return {"token_classfier":token_classification_out, "sequence_classfier": seq_classification_out}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}