Update app.py

app.py

@@ -1,27 +1,21 @@
-import gradio as gr
-from transformers import AutoModelForSequenceClassification, AutoTokenizer
+
+    import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
 # Load the model and tokenizer
-model_name = 'FridayMaster/fine_tune_embedding'  # Replace with your model's repository name
+model_name = 'FridayMaster/fine_tune_embedding'
 tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForSequenceClassification.from_pretrained(model_name)  # Use the appropriate class
+model = AutoModelForCausalLM.from_pretrained(model_name)  # Use the appropriate class
 
 # Define a function to generate responses
 def generate_response(prompt):
     # Tokenize the input prompt
     inputs = tokenizer(prompt, return_tensors="pt", padding=True, truncation=True, max_length=512)
     with torch.no_grad():
-        # Get the model output
-        outputs = model(**inputs)
-    
-    # Process the output logits
-    logits = outputs.logits
-    predicted_class_id = logits.argmax().item()
-    
-    # Generate a response based on the predicted class
-    response = f"Predicted class ID: {predicted_class_id}"
-    
+        # Generate a response using the model
+        outputs = model.generate(inputs['input_ids'], max_length=150, num_return_sequences=1)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
     return response
 
 # Create a Gradio interface