prithivMLmods commited on
Commit
e6ad0c0
•
1 Parent(s): 4af0eb2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +62 -0
README.md CHANGED
@@ -52,6 +52,68 @@ The model uses `bert-base-uncased` as the pre-trained backbone and is fine-tuned
52
  - **Loss:** Cross-Entropy
53
 
54
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
 
56
  ## **🚀 How to Train the Model**
57
 
 
52
  - **Loss:** Cross-Entropy
53
 
54
  ---
55
+ ## Gradio Build
56
+
57
+ ```python
58
+ import gradio as gr
59
+ import torch
60
+ from transformers import BertTokenizer, BertForSequenceClassification
61
+
62
+ # Load the pre-trained BERT model and tokenizer
63
+ MODEL_PATH = "prithivMLmods/Spam-Bert-Uncased"
64
+ tokenizer = BertTokenizer.from_pretrained(MODEL_PATH)
65
+ model = BertForSequenceClassification.from_pretrained(MODEL_PATH)
66
+
67
+ # Function to predict if a given text is Spam or Ham
68
+ def predict_spam(text):
69
+ # Tokenize the input text
70
+ inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
71
+
72
+ # Perform inference
73
+ with torch.no_grad():
74
+ outputs = model(**inputs)
75
+ logits = outputs.logits
76
+ prediction = torch.argmax(logits, axis=-1).item()
77
+
78
+ # Map prediction to label
79
+ if prediction == 1:
80
+ return "Spam"
81
+ else:
82
+ return "Ham"
83
+
84
+
85
+ # Gradio UI - Input and Output components
86
+ inputs = gr.Textbox(label="Enter Text", placeholder="Type a message to check if it's Spam or Ham...")
87
+ outputs = gr.Label(label="Prediction")
88
+
89
+ # List of example inputs
90
+ examples = [
91
+ ["Win $1000 gift cards now by clicking here!"],
92
+ ["You have been selected for a lottery."],
93
+ ["Hello, how was your day?"],
94
+ ["Earn money without any effort. Click here."],
95
+ ["Meeting tomorrow at 10 AM. Don't be late."],
96
+ ["Claim your free prize now!"],
97
+ ["Are we still on for dinner tonight?"],
98
+ ["Exclusive offer just for you, act now!"],
99
+ ["Let's catch up over coffee soon."],
100
+ ["Congratulations, you've won a new car!"]
101
+ ]
102
+
103
+ # Create the Gradio interface
104
+ gr_interface = gr.Interface(
105
+ fn=predict_spam,
106
+ inputs=inputs,
107
+ outputs=outputs,
108
+ examples=examples,
109
+ title="Spam Detection with BERT",
110
+ description="Type a message in the text box to check if it's Spam or Ham using a pre-trained BERT model."
111
+ )
112
+
113
+ # Launch the application
114
+ gr_interface.launch()
115
+
116
+ ```
117
 
118
  ## **🚀 How to Train the Model**
119