Update Dockerfile

Dockerfile

@@ -1,10 +1,10 @@
-# Use lightweight Python base image
+# Use lightweight Python image
 FROM python:3.10-slim
 
 # Set working directory
 WORKDIR /app
 
-# Install system dependencies (for PyTorch and git)
+# Install system dependencies
 RUN apt-get update && apt-get install -y git && rm -rf /var/lib/apt/lists/*
 
 # Copy requirements and install
@@ -14,25 +14,13 @@ RUN pip install --no-cache-dir -r requirements.txt
 # Copy application code
 COPY . .
 
-# ✅ Hugging Face cache directory (use /tmp, writable in Spaces)
-# ENV HF_HOME=/tmp
-# ✅ Hugging Face cache directory (writable path)
+# Hugging Face cache directory
 ENV HF_HOME=/app/.cache/huggingface
+ENV TRANSFORMERS_CACHE=/app/.cache/huggingface
 RUN mkdir -p /app/.cache/huggingface
 
-# Pre-download model into /tmp to avoid cold start
-# RUN python -c "from transformers import AutoTokenizer, AutoModelForCausalLM; \
-    # model_id='rabiyulfahim/qa_python_gpt2'; \
-    # AutoTokenizer.from_pretrained(model_id, cache_dir='/tmp'); \
-    # AutoModelForCausalLM.from_pretrained(model_id, cache_dir='/tmp')"
-# Pre-download model into /tmp to avoid cold start
-RUN python -c "from transformers import AutoTokenizer, AutoModelForCausalLM; \
-    model_id='deepseek-ai/DeepSeek-R1'; \
-    AutoTokenizer.from_pretrained(model_id, cache_dir='/app/.cache/huggingface'); \
-    AutoModelForCausalLM.from_pretrained(model_id, cache_dir='/app/.cache/huggingface')"
-
-# Expose the correct port (Hugging Face default is 7860)
+# Expose FastAPI port
 EXPOSE 7860
 
-# Command to run the app
-CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
+# Command to run FastAPI app
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]