Upload 9 files

This pretrained model has been trained on more than 20k messages and helps classify between advertisements and financial messages.

code/inference.py

@@ -0,0 +1,28 @@
+# Environment variables
+MODEL_PATH = os.environ.get('MODEL_PATH', '/opt/ml/model')
+
+# Load the model
+def model_fn(model_dir):
+    model_file = os.path.join(model_dir, 'xgboost-model')
+    model = model
+    model.load_model(model_file)
+    return model
+# Deserialize the input data
+def input_fn(request_body, request_content_type):
+    if request_content_type == 'application/json':
+        input_data = json.loads(request_body)
+        return np.array(input_data['instances'])
+    else:
+        raise ValueError("Unsupported content type: {}".format(request_content_type))
+# Serialize the output data
+def output_fn(prediction, response_content_type):
+    if response_content_type == 'application/json':
+        response = json.dumps({'predictions': prediction.tolist()})
+        return response
+    else:
+        raise ValueError("Unsupported content type: {}".format(response_content_type))
+# Make predictions
+def predict_fn(input_data, model):
+    dmatrix = model.DMatrix(input_data)
+    prediction = model.predict(dmatrix)
+    return prediction

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.42.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.tar.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca48cb3636ae6a3814eb6b7547a35f9e3a2ae8d24f1a8b677ee33de37e5726da
+size 405902580

special_tokens_map.json

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

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64cba25f2467cfbd2b33b931b76099d75faa67f80f1e272fae192a6d23a48dc6
+size 438223128

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}