Update app.py

app.py

@@ -12,8 +12,10 @@ from llama_cpp import Llama
 @st.cache_resource
 def load_model():
     return Llama.from_pretrained(
-        repo_id="Mykes/med_gemma7b_gguf",
-        filename="*Q4_K_M.gguf",
+        # repo_id="Mykes/med_gemma7b_gguf",
+        # filename="*Q4_K_M.gguf",
+        repo_id="Mykes/med_phi3-mini-4k-GGUF",
+        filename="*Q8_0.gguf",
         verbose=False,
         n_ctx=256,
         n_batch=256,
@@ -22,7 +24,8 @@ def load_model():
 
 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:"
+# 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:"
+basic_prompt = "Q: {question}\nA:"
 input_text = st.text_input('text')
 model_input = basic_prompt.format(question=input_text)