Updates

app.py

@@ -1,5 +1,4 @@
 import streamlit as st
-pip install transformers
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
 st.set_page_config(page_title="Hugging Face Chatbot", layout="centered")
@@ -27,7 +26,7 @@ chat_pipeline = load_model()
 if "messages" not in st.session_state:
     st.session_state.messages = []
 
-# Display chat messages from history on app rerun
+# Display chat messages from history
 for message in st.session_state.messages:
     with st.chat_message(message["role"]):
         st.markdown(message["content"])
@@ -40,12 +39,9 @@ if prompt := st.chat_input("Ask me anything:"):
 
     # Generate response
     with st.spinner("Thinking..."):
-        # Using the pipeline to generate a response
         response = chat_pipeline(prompt)[0]["generated_text"]
-        
-        # The model may return the prompt + response concatenated, so you might need
-        # to extract only the response part. This depends on how the model is trained.
-        # Here we assume the model returns the full text and we just remove the original prompt from it:
+        # The model might return the prompt + response together.
+        # If that's the case, remove the prompt from the start.
         if response.startswith(prompt):
             response = response[len(prompt):].strip()
 

requirements.txt

@@ -0,0 +1,3 @@
+streamlit
+transformers
+torch