Update Dockerfile

Dockerfile

@@ -1,46 +1,37 @@
-# Use the same PyTorch base image that worked for your clustering job
-FROM pytorch/pytorch:2.3.0-cuda12.1-cudnn8-runtime
-
-# Install system basics
-RUN apt-get update && \
-    apt-get install -y wget ca-certificates git && \
-    rm -rf /var/lib/apt/lists/*
-
-WORKDIR /app
-
-# Install Python dependencies
-COPY requirements.txt ./
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Create non-root user and setup the Persistent Storage paths
-# This ensures /data is writable, which is where your Parquet inputs/outputs will live
-RUN useradd -m -u 1000 appuser && \
-    mkdir -p /data/.cache && \
-    mkdir -p /data/out && \
-    mkdir -p /data/input && \
-    chown -R appuser:appuser /data
-
-# Set environment variables to force all Hugging Face caches to the persistent volume
-ENV HF_HOME=/data/.cache \
-    HF_HUB_CACHE=/data/.cache/hub \
-    TRANSFORMERS_CACHE=/data/.cache/transformers \
-    HF_DATASETS_CACHE=/data/.cache/datasets \
-    SENTENCE_TRANSFORMERS_HOME=/data/.cache/sentence_transformers \
-    TOKENIZERS_PARALLELISM=false \
-    OMP_NUM_THREADS=1
-
-# Copy your Miner script and the required Config JSONs
-# Make sure you upload these JSONs to the Space Files along with this Dockerfile!
-COPY sys7_miner.py .
-COPY system7_lexicons.json .
-COPY label_orders.json .
-COPY slang_lexicon.json .
-# COPY sys7_phrase_lexicons_desc_only.json .  <-- Uncomment if you use this
-
-# Copy the runner script
-COPY start.sh .
-RUN chmod +x start.sh && chown -R appuser:appuser /app
-
-USER appuser
-
-CMD ["./start.sh"]
+FROM nvidia/cuda:12.4.1-cudnn-runtime-ubuntu22.04
+
+# 1. Install Python, git, AND 'dos2unix' (the magic fixer tool)
+RUN apt-get update && apt-get install -y \
+    python3.10 \
+    python3-pip \
+    git \
+    git-lfs \
+    dos2unix \
+    && rm -rf /var/lib/apt/lists/*
+
+# 2. Set up Python alias
+RUN ln -s /usr/bin/python3.10 /usr/bin/python
+
+WORKDIR /app
+
+# 3. Install Python dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir -r requirements.txt
+
+# 4. Copy all your scripts and configs
+COPY sys7_miner.py .
+COPY system7_lexicons.json .
+COPY label_orders.json .
+COPY slang_lexicon.json .
+COPY run_job.py .
+
+# 5. THE FIX: Convert all scripts to Unix line endings
+# This fixes 'run_job.py' and any other text file that might have Windows formatting
+RUN dos2unix run_job.py sys7_miner.py
+
+# 6. Permissions
+RUN chmod +x run_job.py
+
+# 7. Run the job
+CMD ["python", "run_job.py"]