Added Gradio app, model files, and dependencies

app.py

@@ -0,0 +1,56 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+# Load the tokenizer and model from the model folder
+tokenizer = AutoTokenizer.from_pretrained("./model")
+model = AutoModelForSequenceClassification.from_pretrained("./model", trust_remote_code=True)
+
+# Set the device (CPU or GPU)
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+model = model.to(device)
+
+# Define topic mapping
+topic_mapping = {
+    0: 'Bank Account Services',
+    1: 'Credit Card or Prepaid Card',
+    2: 'Others',
+    3: 'Theft/Dispute Reporting',
+    4: 'Mortgage/Loan'
+}
+
+# Prediction function
+def predict_complaint_topic(complaint_text):
+    encoding = tokenizer.encode_plus(
+        complaint_text,
+        add_special_tokens=True,
+        max_length=128,
+        return_token_type_ids=False,
+        padding='max_length',
+        truncation=True,
+        return_attention_mask=True,
+        return_tensors='pt'
+    )
+    input_ids = encoding['input_ids'].to(device)
+    attention_mask = encoding['attention_mask'].to(device)
+    
+    with torch.no_grad():
+        outputs = model(input_ids=input_ids, attention_mask=attention_mask)
+        logits = outputs.logits
+        predicted_class_id = torch.argmax(logits, dim=1).item()
+    
+    predicted_topic = topic_mapping[predicted_class_id]
+    return predicted_topic
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=predict_complaint_topic,  # Function to call for prediction
+    inputs=gr.Textbox(label="Enter your complaint text"),  # Input type (Textbox)
+    outputs=gr.Textbox(label="Predicted Complaint Topic"),  # Output type (Textbox)
+    live=True,  # Enable live prediction as the user types
+    title="Complaint Topic Classifier",  # Title of the app
+    description="This model classifies complaints into different topics like 'Bank Account Services', 'Credit Card or Prepaid Card', etc."  # Description of the app
+)
+
+# Launch the interface
+iface.launch()

model/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "vocab_size": 30522
+}

model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9694300978a62b025d9cb16b3f7114e4761a6808bfbbbb27d527d5bf4aa83d1f
+size 267841796

model/special_tokens_map.json

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

model/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

requirements.txt

@@ -0,0 +1,4 @@
+gradio
+torch
+transformers
+safetensors