Update Dockerfile

Dockerfile

@@ -8,21 +8,25 @@ RUN python3 -m venv /opt/venv
 ENV PATH="/opt/venv/bin:$PATH"
 RUN pip install -U pip huggingface_hub
 
-# Download Gemma 4 26B (via huggingface_hub)
+# Define the build argument for the token
+ARG HF_TOKEN
+
+# Download Gemma 4 26B using the token to prevent the warning and rate-limiting
 RUN python3 -c 'from huggingface_hub import hf_hub_download; \
+    import os; \
+    token = os.getenv("HF_TOKEN") or None; \
     repo="unsloth/gemma-4-26B-A4B-it-GGUF"; \
-    hf_hub_download(repo_id=repo, filename="gemma-4-26B-A4B-it-UD-Q4_K_XL.gguf", local_dir="/app"); \
-    hf_hub_download(repo_id=repo, filename="mmproj-BF16.gguf", local_dir="/app")'
+    hf_hub_download(repo_id=repo, filename="gemma-4-26B-A4B-it-UD-Q4_K_XL.gguf", local_dir="/app", token=token); \
+    hf_hub_download(repo_id=repo, filename="mmproj-BF16.gguf", local_dir="/app", token=token)'
 
-# Download Gemma 4 E2B + Speculative Setup (via wget into /app)
+# Download Gemma 4 E2B + Speculative Setup
 RUN wget "https://huggingface.co/unsloth/gemma-4-E2B-it-qat-GGUF/resolve/main/gemma-4-E2B-it-qat-UD-Q4_K_XL.gguf" -O /app/gemma-4-E2B-it-qat-UD-Q4_K_XL.gguf && \
     wget "https://huggingface.co/unsloth/gemma-4-E2B-it-qat-GGUF/resolve/main/mtp-gemma-4-E2B-it.gguf" -O /app/mtp-gemma-4-E2B-it.gguf && \
     wget "https://huggingface.co/unsloth/gemma-4-E2B-it-qat-GGUF/resolve/main/mmproj-F16.gguf" -O /app/gemma-4-E2B-it-mmproj.gguf
 
-# Download Gemma 3 1B Model (via wget into /app)
+# Download Gemma 3 1B Model
 RUN wget "https://huggingface.co/MaziyarPanahi/gemma-3-1b-it-GGUF/resolve/main/gemma-3-1b-it.Q3_K_M.gguf" -O /app/gemma-3-1b-it.Q3_K_M.gguf
 
-# Launching with the explicit Gemma 4 26B configuration
 CMD ["--server", \
      "-m", "/app/gemma-4-26B-A4B-it-UD-Q4_K_XL.gguf", \
      "--mmproj", "/app/mmproj-BF16.gguf", \