Update README.md

README.md

@@ -16,7 +16,7 @@ A Qwen3.5-**0.8B** model served as a **pure model**: this Space is a thin pass-t
 On startup it:
 1. Downloads `Qwen3.5-0.8B.Q4_K_M.gguf` from
    [`anon334test/qwopus`](https://huggingface.co/anon334test/qwopus)
-   (a mirror of `Jackrong/Qwopus3.5-0.8B-v3-GGUF` — already GGUF, no conversion).
+
 2. Serves it with prebuilt llama.cpp `llama-server` (release `b9664`, no compilation) behind an
    OpenAI-compatible FastAPI proxy + a multi-turn chat UI with a collapsible "Thinking" panel.