Update Dockerfile

Dockerfile

@@ -1,11 +1,5 @@
-# ---------------------------------------------------------
-# Dockerfile for HuggingFace Spaces (Custom Docker Runtime)
-# Runs FastAPI + llama-cpp-python + GGUF model
-# ---------------------------------------------------------
-
 FROM python:3.11-slim
 
-# Install system dependencies required by llama-cpp-python
 RUN apt-get update && apt-get install -y --no-install-recommends \
     build-essential \
     cmake \
@@ -15,34 +9,20 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     libopenblas-dev \
     && rm -rf /var/lib/apt/lists/*
 
-# Set the working directory
 WORKDIR /code
 
-# Copy requirements first (for better Docker cache)
 COPY requirements.txt /code/requirements.txt
-
-# Install Python dependencies
 RUN pip install --no-cache-dir --upgrade pip \
     && pip install --no-cache-dir -r /code/requirements.txt
 
-# Copy application file
 COPY app.py /code/app.py
 
-# Copy your model folder (GGUF file)
-COPY model /code/model
+# Copy model (NO folder needed)
+COPY Phi-3.1-mini-4k-instruct-IQ2_M.gguf /code/
 
-# Environment variables for llama.cpp backend
-ENV MODEL_PATH=/code/model/Phi-3.1-mini-4k-instruct-IQ2_M.gguf
-ENV N_THREADS=4
-ENV N_CTX=4096
-ENV N_BATCH=512
-ENV N_GPU_LAYERS=0
-ENV MAX_CONCURRENT_REQUESTS=6
-ENV PYTHONUNBUFFERED=1
+ENV MODEL_PATH=/code/Phi-3.1-mini-4k-instruct-IQ2_M.gguf
 
-# HuggingFace Spaces requires server to run on port 7860
 EXPOSE 7860
 
-# Start FastAPI with uvicorn
 CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]