Switch to TinyLlama 1.1B Chat (llama.cpp-supported)

Dockerfile

@@ -7,10 +7,10 @@ RUN set -eux; \
   elif command -v apt-get >/dev/null 2>&1; then apt-get update && apt-get install -y --no-install-recommends curl ca-certificates && rm -rf /var/lib/apt/lists/*; \
   else echo "no supported pkg manager" && exit 1; fi
 
-# bake the Liquid AI GGUF at build time (fail build if download fails)
+# bake tiny model into the image (fail build if download fails)
 RUN mkdir -p /models && \
     curl -fL --retry 5 --retry-delay 2 -o /models/model.gguf \
-    "https://huggingface.co/LiquidAI/LFM2-350M-GGUF/resolve/main/LFM2-350M-Q4_K_M.gguf?download=true"
+    "https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf?download=true"
 
 EXPOSE 7860
 # base image ENTRYPOINT is ["llama-server"]; pass only args: