Create Dockerfile

Dockerfile

@@ -0,0 +1,20 @@
+# Use the official PyTorch image with CUDA support
+FROM pytorch/pytorch:2.0.0-cuda11.7-cudnn8-runtime
+
+# Install git to clone the model repository
+RUN apt-get update && apt-get install -y git
+
+# Install other dependencies
+RUN pip install transformers
+
+# Clone the unsloth/llama-3-8b-bnb-4bit model repository
+RUN git clone https://huggingface.co/unsloth/llama-3-8b-bnb-4bit
+
+# Set the working directory to the model directory
+WORKDIR /unsloth/llama-3-8b-bnb-4bit
+
+# Copy the inference script
+COPY inference.py .
+
+# Run the inference script
+CMD ["python", "inference.py"]