Update app.py

app.py

@@ -1,22 +1,25 @@
 import streamlit as st
-from llama_cpp import Llama
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-# Load the GGUF model
+# Load the model and tokenizer
 @st.cache_resource
 def load_model():
-    model_path = "shanthi-323/lora_model_qnachatbot_cbt_q4_k_m"  # Ensure this path matches your uploaded GGUF model file
-    return Llama(model_path=model_path)
+    model_name = "shanthi-323/model"
+    tokenizer = AutoTokenizer.from_pretrained(model_name)
+    model = AutoModelForCausalLM.from_pretrained(model_name)
+    return tokenizer, model
 
-llm = load_model()
+tokenizer, model = load_model()
 
-st.title("Chat with GGUF Model")
-st.write("Start interacting with your fine-tuned chatbot!")
+st.title("AI Chatbot")
+st.write("Chat with your fine-tuned model!")
 
 # User input
 user_input = st.text_input("You: ", placeholder="Type your message here...")
 
 if user_input:
-    # Generate a response using llama-cpp-python
-    response = llm(user_input)
-    st.text_area("Bot:", value=response["choices"][0]["text"].strip(), height=200)
+    inputs = tokenizer(user_input, return_tensors="pt")
+    outputs = model.generate(inputs["input_ids"], max_length=100)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    st.text_area("Bot:", value=response, height=200, max_chars=None)