Update app.py

app.py

@@ -1,14 +1,26 @@
 import streamlit as st
 from llama_cpp import Llama
 
-llm = Llama.from_pretrained(
-    repo_id="Mykes/med_gemma7b_gguf",
-    filename="*Q4_K_M.gguf",
-    verbose=False,
-    n_ctx=512,
-    n_batch=512,
-    n_threads=4
-)
+# llm = Llama.from_pretrained(
+#     repo_id="Mykes/med_gemma7b_gguf",
+#     filename="*Q4_K_M.gguf",
+#     verbose=False,
+#     n_ctx=512,
+#     n_batch=512,
+#     n_threads=4
+# )
+@st.cache_resource
+def load_model():
+    return Llama.from_pretrained(
+        repo_id="Mykes/med_gemma7b_gguf",
+        filename="*Q4_K_M.gguf",
+        verbose=False,
+        n_ctx=256,
+        n_batch=256,
+        n_threads=4
+    )
+
+llm = load_model()
 
 basic_prompt = "Below is the context which is your conversation history and the last user question. Write a response according the context and question. ### Context: user: Ответь мне на вопрос о моем здоровье. assistant: Конечно! Какой у Вас вопрос? ### Question: {question} ### Response:"
 input_text = st.text_input('text')