Upload app.py

app.py

@@ -0,0 +1,46 @@
+import streamlit as st
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
+import torch
+
+# Load model and tokenizer
+MODEL_NAME = "lora_model"  # Thay thế bằng tên mô hình thực tế của bạn
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, torch_dtype=torch.float16, device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+
+def generate_response(prompt):
+    """Generate a response from the model."""
+    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+    streamer = TextStreamer(tokenizer)
+    with torch.no_grad():
+        model.generate(**inputs, streamer=streamer, max_length=512)
+    return ""
+
+# Streamlit UI
+st.set_page_config(page_title="Chatbot", page_icon="🤖")
+st.title("🤖 AI Chatbot")
+
+# Initialize chat history if not exists
+if "messages" not in st.session_state:
+    st.session_state.messages = []
+
+# Display chat messages
+for message in st.session_state.messages:
+    with st.chat_message(message["role"]):
+        st.markdown(message["content"])
+
+# User input
+user_input = st.chat_input("Nhập tin nhắn...")
+if user_input:
+    # Append user message
+    st.session_state.messages.append({"role": "user", "content": user_input})
+    with st.chat_message("user"):
+        st.markdown(user_input)
+
+    # Generate response
+    with st.chat_message("assistant"):
+        response = generate_response(user_input)
+        st.markdown(response)
+
+    # Append assistant response
+    st.session_state.messages.append({"role": "assistant", "content": response})
+