Update app.py

app.py

@@ -3,19 +3,15 @@ import json
 from transformers import AutoModelForSequenceClassification, Trainer, TrainingArguments, AutoTokenizer
 from datasets import Dataset
 
-# Load preprocessed and tokenized data
-def load_data(preprocessed_file, tokenized_file):
-    with open(preprocessed_file.name, 'r') as f:
-        preprocessed_data = json.load(f)
-    
+# Load tokenized data
+def load_data(tokenized_file):
     with open(tokenized_file.name, 'r') as f:
         tokenized_data = json.load(f)
-    
-    return preprocessed_data, tokenized_data
+    return tokenized_data
 
 # Fine-tune the model
-def fine_tune_model(preprocessed_file, tokenized_file, progress=gr.Progress()):
-    preprocessed_data, tokenized_data = load_data(preprocessed_file, tokenized_file)
+def fine_tune_model(tokenized_file, progress=gr.Progress()):
+    tokenized_data = load_data(tokenized_file)
     
     # Convert tokenized data to Dataset
     dataset = Dataset.from_dict(tokenized_data)
@@ -60,12 +56,11 @@ def fine_tune_model(preprocessed_file, tokenized_file, progress=gr.Progress()):
 iface = gr.Interface(
     fn=fine_tune_model,
     inputs=[
-        gr.File(label="Upload Preprocessed Data JSON"),
         gr.File(label="Upload Tokenized Data JSON")
     ],
     outputs=gr.Textbox(label="Processing Information"),
     title="Fine-Tune Patent BERT Model",
-    description="Upload preprocessed and tokenized JSON files to fine-tune the BERT model.",
+    description="Upload tokenized JSON file to fine-tune the BERT model.",
     live=True  # Enable live updates for progress
 )