Update Dockerfile

Dockerfile

@@ -1,27 +1,28 @@
-# Use slim base for smaller size on free CPU tier
 FROM python:3.10-slim
 
-# Install minimal build tools only if any C extensions are needed (nanochat is mostly pure torch/Python)
+# We NEED rustc and cargo to build the tokenizer
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    build-essential git curl \
+    build-essential git curl rustc cargo \
     && rm -rf /var/lib/apt/lists/*
 
 WORKDIR /app
 
-# Copy requirements first for better caching
+# 1. Clone the missing rustbpe source directly into the container
+RUN git clone https://github.com/karpathy/rustbpe.git
+
+# 2. Install maturin and build the rustbpe package
+RUN pip install --no-cache-dir maturin \
+    && cd rustbpe && maturin develop --release
+
+# 3. Install the rest of the requirements
 COPY requirements.txt .
 RUN pip install --no-cache-dir -r requirements.txt \
     && pip install --no-cache-dir torch --index-url https://download.pytorch.org/whl/cpu
 
-# Copy the rest of your project (nanochat/, weights, app.py, etc.)
+# Copy your project files
 COPY . .
 
-# Clean up pip cache to save space
-RUN pip cache purge
-
-# Gradio defaults
 EXPOSE 7860
 ENV GRADIO_SERVER_NAME="0.0.0.0"
 
-# Run the app
 CMD ["python", "app.py"]