Update Dockerfile

Dockerfile

@@ -20,17 +20,16 @@ WORKDIR $HOME/app
 RUN pip install --no-cache-dir --upgrade pip
 RUN pip install --no-cache-dir huggingface_hub llama-cpp-python[server]
 
-# Sťahovanie modelu - OPRAVENÝ PRÍKAZ
-# Používame --include na špecifikáciu konkrétneho GGUF súboru
+
+# Zmeň v kroku 3 na:
 RUN huggingface-cli download bartowski/Qwen2.5-Coder-7B-Instruct-GGUF \
-    Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf \
-    --local-dir . \
-    --local-dir-use-symlinks False
+    Qwen2.5-Coder-7B-Instruct-Q8_0.gguf \
+    --local-dir . --local-dir-use-symlinks False
 
-# Spustenie servera
-# Pridaný parameter --n_ctx pre kontextové okno (uprav podľa RAM v Space)
+# Zmeň v kroku 4 (CMD) na:
 CMD ["python3", "-m", "llama_cpp.server", \
-     "--model", "Qwen2.5-Coder-7B-Instruct-Q4_K_M.gguf", \
+     "--model", "Qwen2.5-Coder-7B-Instruct-Q8_0.gguf", \
      "--host", "0.0.0.0", \
      "--port", "7860", \
+     "--n_ctx", "8192", \
      "--chat_format", "chatml"]