Create test2.py

test2.py

@@ -0,0 +1,50 @@
+from transformers import BertTokenizer, BertModel
+import torch
+from torch.utils.data import DataLoader
+
+# Step 1: Preprocess Your Data
+# Sample student resumes and internship job descriptions
+student_resume_1 = "I have experience in Python programming and data analysis."
+internship_job_description_1 = "Looking for a data analyst intern proficient in Python and SQL."
+
+student_resume_2 = "Experienced in web development with HTML, CSS, and JavaScript."
+internship_job_description_2 = "Seeking a web development intern skilled in HTML, CSS, and JavaScript."
+
+# Step 2: Tokenization
+# Load pre-trained BERT tokenizer
+tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
+
+# Step 3: Encoding Inputs
+# Tokenize and encode the text data
+encoded_student_resume_1 = tokenizer(student_resume_1, padding=True, truncation=True, return_tensors='pt')
+encoded_internship_job_description_1 = tokenizer(internship_job_description_1, padding=True, truncation=True, return_tensors='pt')
+
+encoded_student_resume_2 = tokenizer(student_resume_2, padding=True, truncation=True, return_tensors='pt')
+encoded_internship_job_description_2 = tokenizer(internship_job_description_2, padding=True, truncation=True, return_tensors='pt')
+
+# Step 4: Batching and Data Loading
+# Organize encoded input features into batches
+batch_size = 2
+dataset = [(encoded_student_resume_1, encoded_internship_job_description_1),
+           (encoded_student_resume_2, encoded_internship_job_description_2)]
+dataloader = DataLoader(dataset, batch_size=batch_size)
+
+# Step 5: Feed Data into the Model
+# Load pre-trained BERT model
+model = BertModel.from_pretrained('bert-base-uncased')
+
+# Iterate over batches and feed data into the model
+for batch in dataloader:
+    student_resume_batch, internship_job_description_batch = batch
+
+    # Feed input_ids to the model
+    student_resume_outputs = model(**student_resume_batch)
+    internship_job_description_outputs = model(**internship_job_description_batch)
+
+    # Get model outputs
+    student_resume_last_hidden_states = student_resume_outputs.last_hidden_state
+    internship_job_description_last_hidden_states = internship_job_description_outputs.last_hidden_state
+
+    # Perform further processing or analysis with the model outputs
+    # For example, compute similarity scores between student resumes and internship job descriptions
+    # ...