dload model

Dockerfile

@@ -10,6 +10,7 @@ RUN apt-get update && apt-get install -y \
     curl \
     pkg-config \
     git \
+    wget \
     && rm -rf /var/lib/apt/lists/*
 
 # Install Python deps — compile llama-cpp-python with OpenBLAS
@@ -18,12 +19,15 @@ RUN CMAKE_ARGS="-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS" \
     FORCE_CMAKE=1 \
     pip install --no-cache-dir -r requirements.txt
 
+# Download the model during build
+RUN mkdir -p /app/models && \
+    wget -q https://huggingface.co/unsloth/gemma-4-26B-A4B-it-GGUF/resolve/main/gemma-4-26B-A4B-it-UD-IQ3_XXS.gguf -O /app/models/gemma-4-26B-A4B-it-UD-IQ3_XXS.gguf
+
 COPY app.py .
 
 # HuggingFace Spaces expects port 7860
 EXPOSE 7860
 
-# Set SPACE_URL at runtime via HF Space secrets/env vars
 ENV SPACE_URL=""
 ENV N_CTX="4096"
 ENV N_THREADS="2"