v 0.1

- добавлен системный промт;
- add_generation_prompt=False

app.py

@@ -21,7 +21,7 @@ tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
 def messages_to_prompt(messages):
     messages = [{"role": m.role.value, "content": m.content} for m in messages]
     prompt = tokenizer.apply_chat_template(
-        messages, tokenize=False, add_generation_prompt=True
+        messages, tokenize=False, add_generation_prompt=False
     )
     return prompt