Мне кажется или CLI llama.cpp разучился вытирать реверс-промпт из ChatML-ответов? $ llama-cli -m ./models/openhermes-2.5-neural-chat-7b-v3-1-7b/ggml-model-q5_k_m.gguf -n -1 -t 4 --color -f prompts/chat-with-chatml.txt --prompt-cache ./models/openhermes-2.5-neural-chat-7b-v3-1-7b/ggml-model-q5_k_m_chat-with-chatml.txt.prompt --ctx-size 2048 -cnv --in-prefix &#39;<|im_start|>user\n&#39; --in-suffix &#39;<|im_end|>\n<|im_start|>assistant\n&#39; --reverse-prompt &#39;<|im_end|>&#39; --chat-template chatml ... == Running in interactive mode. == - Press Ctrl+C to interject at any time. - Press Return to return control to the AI. - To return control without starting a new line, end your input with &#39;/&#39;. - If you want to submit another line, end your input with &#39;\&#39;. <|im_start|>system You are a helpful assistant<|im_end|> <|im_start|>user Hello<|im_end|> <|im_start|>assistant Hi there<|im_end|> <|im_start|>user Who are you<|im_end|> <|im_start|>assistant I am an assistant<|im_end|> > Howdy? Hello again<|im_end|> > Вот чего он этот "<|im_end|>" мне показывает?!

https://bbycroft.net/llm - визуализация о том как работает GPT