Update Dockerfile

Dockerfile

@@ -7,17 +7,19 @@ ENV HOME=/home/user \
 
 WORKDIR $HOME/app
 
+# Install only wget and essential libs (skipping heavy build tools like cmake)
 USER root
-RUN apt-get update && apt-get install -y \
-    gcc g++ make cmake git wget \
-    && rm -rf /var/lib/apt/lists/*
+RUN apt-get update && apt-get install -y wget libopenblas-dev && rm -rf /var/lib/apt/lists/*
 USER user
 
-# Install llama-cpp-python and other essentials
-RUN pip install --no-cache-dir llama-cpp-python huggingface_hub gradio
+# USE PRE-COMPILED WHEELS: This skips the "Building Wheel" stage entirely
+RUN pip install --no-cache-dir \
+    --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu \
+    llama-cpp-python
 
-# Download the specific GGUF file from the repo in your screenshot
-# Using the Q4_K_M version for the best balance of speed and logic
+RUN pip install --no-cache-dir huggingface_hub gradio
+
+# Download the GGUF model directly
 RUN huggingface-cli download tensorblock/llama3.2-1b-Uncensored-GGUF \
     llama3.2-1b-Uncensored-Q4_K_M.gguf \
     --local-dir . --local-dir-use-symlinks False