Upload 5 files

app.py

@@ -0,0 +1,35 @@
+import streamlit as st
+from transformers import DistilBertTokenizer, TFDistilBertForSequenceClassification
+import tensorflow as tf
+
+# Load the pre-trained model and tokenizer
+model_path = 'drive-download-20241117T174204Z-001/'
+loaded_model = TFDistilBertForSequenceClassification.from_pretrained(model_path)
+loaded_tokenizer = DistilBertTokenizer.from_pretrained(model_path)
+
+# Define the prediction function
+def predict_with_loaded_model(in_sentences):
+    labels = ["non-stress", "stress"]
+    inputs = loaded_tokenizer(in_sentences, return_tensors="tf", padding=True, truncation=True, max_length=512)
+    predictions = loaded_model(inputs)
+    predicted_labels = tf.argmax(predictions.logits, axis=-1).numpy()
+    predicted_probs = tf.nn.softmax(predictions.logits, axis=-1).numpy()
+
+    return [{"text": sentence, "confidence": probs.tolist(), "label": labels[label]} for sentence, label, probs in zip(in_sentences, predicted_labels, predicted_probs)]
+
+# Streamlit interface
+st.title("Stress Prediction with DistilBERT")
+
+# Add a text input box for the user to enter a sentence
+user_input = st.text_area("Enter a sentence or text:", "")
+
+# When the user clicks "Predict", run the prediction function
+if st.button("Predict"):
+    if user_input:
+        # Make the prediction using the model
+        prediction = predict_with_loaded_model([user_input])[0]
+        st.write(f"Text: {prediction['text']}")
+        st.write(f"Prediction: {prediction['label']}")
+        st.write(f"Confidence: {prediction['confidence']}")
+    else:
+        st.write("Please enter a sentence to predict.")

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "transformers_version": "4.44.2",
+  "vocab_size": 30522
+}

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": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}