Update app.py

app.py

@@ -7,41 +7,14 @@ llm = Llama.from_pretrained(
     verbose=False
 )
 
+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')
+model_input = basic_prompt.format(question=input_text)
 if input_text:
     output = llm(
-      input_text, # Prompt
+      model_input, # Prompt
       max_tokens=32, # Generate up to 32 tokens, set to None to generate up to the end of the context window
-      stop=["Q:", "\n"], # Stop generating just before the model would generate a new question
+      stop=["<end_of_turn>"],
       echo=True # Echo the prompt back in the output
     ) # Generate a completion, can also call create_completion
-    st.write(output)
-
-
-# from ctransformers import AutoModelForCausalLM, AutoTokenizer
-
-# model = AutoModelForCausalLM.from_pretrained("Mykes/med_gemma7b_gguf", model_file="unsloth.Q4_K_M.gguf")
-# tokenizer = AutoTokenizer.from_pretrained(model)
-# input_text = st.textarea('text')
-# if text:
-#     input_ids = tokenizer(input_text, return_tensors="pt")
-#     outputs = model.generate(**input_ids)
-#     st.write(outputs)
-
-
-
-# from transformers import AutoTokenizer, AutoModelForCausalLM
-
-# model_id = "Mykes/med_gemma7b_gguf"
-# filename = "unsloth.Q4_K_M.gguf"
-
-# tokenizer = AutoTokenizer.from_pretrained(model_id, gguf_file=filename)
-# model = AutoModelForCausalLM.from_pretrained(model_id, gguf_file=filename)
-
-
-
-# input_text = st.textarea('text')
-# if text:
-#     input_ids = tokenizer(input_text, return_tensors="pt")
-#     outputs = model.generate(**input_ids)
-#     st.write(outputs)
+    st.write(output["choices"][0]["text"])