Update Dockerfile

Dockerfile

@@ -26,6 +26,20 @@ RUN pip install --no-cache-dir \
     faster-whisper \
     huggingface_hub
 
+# Create models directory
+RUN mkdir -p /data/models
+
+# Pre-download models one by one (so we see progress and can cache layers)
+RUN python -c "from huggingface_hub import hf_hub_download; print('⬇️ Downloading Qwen2.5-0.5B...'); hf_hub_download('Qwen/Qwen2.5-Coder-0.5B-Instruct-GGUF', 'qwen2.5-coder-0.5b-instruct-q4_k_m.gguf', local_dir='/data/models'); print('✅ Done!')"
+
+RUN python -c "from huggingface_hub import hf_hub_download; print('⬇️ Downloading Qwen2.5-1.5B...'); hf_hub_download('Qwen/Qwen2.5-Coder-1.5B-Instruct-GGUF', 'qwen2.5-coder-1.5b-instruct-q4_k_m.gguf', local_dir='/data/models'); print('✅ Done!')"
+
+RUN python -c "from huggingface_hub import hf_hub_download; print('⬇️ Downloading Qwen2.5-3B...'); hf_hub_download('Qwen/Qwen2.5-Coder-3B-Instruct-GGUF', 'qwen2.5-coder-3b-instruct-q4_k_m.gguf', local_dir='/data/models'); print('✅ Done!')"
+
+RUN python -c "from huggingface_hub import hf_hub_download; print('⬇️ Downloading Qwen2.5-7B...'); hf_hub_download('Qwen/Qwen2.5-Coder-7B-Instruct-GGUF', 'qwen2.5-coder-7b-instruct-q4_k_m.gguf', local_dir='/data/models'); print('✅ Done!')"
+
+RUN python -c "from huggingface_hub import hf_hub_download; print('⬇️ Downloading DeepSeek-V2-Lite...'); hf_hub_download('bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF', 'DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M.gguf', local_dir='/data/models'); print('✅ Done!')"
+
 # Copy application
 COPY app.py /app/app.py