Update app.py

app.py

@@ -4,15 +4,42 @@ from sklearn.metrics.pairwise import cosine_similarity
 from keyphrasetransformer import KeyPhraseTransformer
 from wordcloud import WordCloud
 import matplotlib.pyplot as plt
-
+from datasets import load_dataset
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, TrainingArguments, Trainer
+import numpy as np
 
 kp = KeyPhraseTransformer()
 
 @st.cache_resource
-def load_model():
-    model = SentenceTransformer('all-MiniLM-L6-v2')
-    return model
+#def load_model():
+#    model = SentenceTransformer('all-MiniLM-L6-v2')
+#    return model
+#---------------------
+# Prepare and tokenize dataset
+dataset = load_dataset("Sachinkelenjaguri/Resume_dataset")
+tokenizer = AutoTokenizer.from_pretrained("bert-base-cased")
+
+def tokenize_function(examples):
+    return tokenizer(examples["text"], padding="max_length", truncation=True)
+
+tokenized_datasets = dataset.map(tokenize_function, batched=True)
+
+small_train_dataset = tokenized_datasets["train"].shuffle(seed=42).select(range(200))
+small_eval_dataset = tokenized_datasets["test"].shuffle(seed=42).select(range(200))
+
+model = AutoModelForSequenceClassification.from_pretrained("bert-base-cased", num_labels=5)
+training_args = TrainingArguments(output_dir="test_trainer", evaluation_strategy="epoch")
+
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=small_train_dataset,
+    eval_dataset=small_eval_dataset,
+    compute_metrics=compute_metrics,
+)
 
+trainer.train()
+#---------------------
 def calculate_similarity(model, text1, text2):
     embedding1 = model.encode([text1])
     embedding2 = model.encode([text2])