Update chatbot.py

chatbot.py

@@ -1,34 +1,26 @@
 import streamlit as st
 from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline, BitsAndBytesConfig
 import torch
-from huggingface_hub import login
-import os
 
-# Authenticate with secret token
-login(token=os.getenv("HF_TOKEN"))
 # ================= CACHE THE MODEL =================
 @st.cache_resource
 def load_model():
-    model_id = "ammoncoder123/IPTchatbotModel-1.7B" 
+    model_id = "ammoncoder123/IPTchatbotModel1-1.7B"
 
-    st.write("Loading tokenizer...")
-    tokenizer = AutoTokenizer.from_pretrained(model_id)
-
-    st.write("Loading model (this may take a few minutes the first time)...")
     quantization_config = BitsAndBytesConfig(
         load_in_4bit=True,
         bnb_4bit_compute_dtype=torch.float16
     )
 
+    tokenizer = AutoTokenizer.from_pretrained(model_id)
     model = AutoModelForCausalLM.from_pretrained(
         model_id,
         quantization_config=quantization_config,
-        device_map="auto",  # GPU if available, else CPU
+        device_map="auto",
         torch_dtype=torch.float16,
-        trust_remote_code=True  # Safe for most models
+        trust_remote_code=True
     )
 
-    st.write("Model loaded successfully!")
     return pipeline(
         "text-generation",
         model=model,
@@ -44,7 +36,7 @@ pipe = load_model()
 # ==================== CHAT INTERFACE ====================
 st.title("My 1.7B Fine-Tuned IPT Chatbot")
 
-st.info("⚠️ Small fine-tuned model (1.7B). Answers may vary — verify important info.")
+st.info("Small fine-tuned model (1.7B). Answers may vary — verify facts.")
 
 if "messages" not in st.session_state:
     st.session_state.messages = []
@@ -63,7 +55,7 @@ if prompt := st.chat_input("Ask about IPT, ICT, or anything..."):
             chat_messages = [{"role": "user", "content": prompt}]
             outputs = pipe(chat_messages, max_new_tokens=300, temperature=0.7, do_sample=True, top_p=0.9)
             response = outputs[0]["generated_text"]
-            if response.startswith(prompt):
+            if isinstance(response, str) and response.startswith(prompt):
                 response = response[len(prompt):].strip()
             st.markdown(response)