Add application file

app.py

@@ -0,0 +1,49 @@
+import gradio as gr
+import tensorflow as tf
+import numpy as np
+from transformers import TFAutoModelForSequenceClassification, DistilBertTokenizer
+from huggingface_hub import hf_hub_download
+
+# Define the repository name and model ID
+repository_name = "MariamKili/my_bert_model"
+model_id = "tf_model"
+
+# Load the tokenizer
+tokenizer = DistilBertTokenizer.from_pretrained("distilbert-base-uncased")
+
+# Load the model directly from Hugging Face Hub
+model = TFAutoModelForSequenceClassification.from_pretrained(repository_name)
+
+# Your prediction function would remain the same
+def predict_sentiment(text):
+    # Tokenize and encode the input text
+    encoded_input = tokenizer.encode_plus(
+        text,
+        add_special_tokens=True,
+        max_length=512,
+        padding="max_length",
+        return_attention_mask=True,
+        truncation=True,
+        return_tensors="tf"
+    )
+
+    # Make predictions
+    output = model(encoded_input)
+    probabilities = tf.nn.softmax(output.logits, axis=1).numpy()[0]
+    predicted_label = np.argmax(probabilities)
+    confidence_score = probabilities[predicted_label]
+
+    # Decode the predicted label
+    label = "positive" if predicted_label == 1 else "negative"
+
+    return label, confidence_score
+
+
+# Create the Gradio interface
+text_input = gr.components.Textbox(lines=5, label="Enter your text here")
+output_text = gr.components.Textbox(label="Predicted Sentiment")
+
+# Define the Gradio interface
+iface=gr.Interface(fn=predict_sentiment, inputs=text_input, outputs=output_text, title="Sentiment Analysis Application System")
+# Launch the Gradio app
+iface.launch(share=True)

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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}