trial for docker unzipping

app.py

@@ -1,10 +1,36 @@
 import torch
 import torch.nn.functional as F  # Importing the functional module for softmax
 from torch import nn
+import zipfile
 import gradio as gr
+from transformers import BertTokenizer, BertForSequenceClassification
 import os
 
+model_zip_path = "BioBERT_Model.zip"
+tokenizer_zip_path = "BioBERT_Tokenizer.zip"
+
 # Assume model and tokenizer are already loaded
+def load_model_and_tokenizer():
+    if not os.path.exists('BioBERT_Model'):
+        with zipfile.ZipFile(model_zip_path, 'r') as zip_ref:
+            zip_ref.extractall('BioBERT_Model')
+
+    if not os.path.exists('BioBERT_Tokenizer'):
+        with zipfile.ZipFile(tokenizer_zip_path, 'r') as zip_ref:
+            zip_ref.extractall('BioBERT_Tokenizer')
+
+    model_path = 'BioBERT_Model/content/BioBERT_Model'
+    tokenizer_path = 'BioBERT_Tokenizer/content/BioBERT_Tokenizer'
+
+    model = BertForSequenceClassification.from_pretrained(model_path)
+    tokenizer = BertTokenizer.from_pretrained(tokenizer_path)
+
+    return model, tokenizer
+
+
+model, tokenizer = load_model_and_tokenizer()
+device = "cpu"
+model = model.to(device)
 
 def predict_drug_target_interaction(sentence):
     # Tokenize the input sentence
@@ -155,4 +181,4 @@ with gr.Blocks() as demo:
 
 
 # Launch the interface
-demo.launch()
+demo.launch()