Update app.py

app.py

@@ -1,7 +1,6 @@
 import streamlit as st
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
-from PIL import Image
 import os
 
 
@@ -24,7 +23,7 @@ if not tokenizer or not model:
     st.stop()
 
 # Default to CPU
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+device = torch.device("cpu")
 if model is not None:
     model = model.to(device)
 
@@ -39,14 +38,20 @@ for message in st.session_state.messages:
 
 def generate_response(prompt):
     try:
-        inputs = tokenizer(prompt, return_tensors="pt").to(device)  # Ensure inputs are moved to the device (CPU)
-        outputs = model.generate(**inputs, max_new_tokens=150, temperature=0.7)
+        # Tokenize the input prompt
+        inputs = tokenizer(prompt, return_tensors="pt").to(device)
+
+        # Make sure that inputs are passed properly to the model
+        outputs = model.generate(inputs["input_ids"], max_new_tokens=150, temperature=0.7)
+        
+        # Decode the output to text
         response = tokenizer.decode(outputs[0], skip_special_tokens=True)
         return response
     except Exception as e:
         st.error(f"Error during text generation: {e}")
         return "Sorry, I couldn't process your request."
 
+
 user_input = st.chat_input("Type your gardening question here:")
 
 if user_input: