Merge branch 'main' of hf.co:spaces/TheDrakosfire/CollectibleCardGenerator

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 *.png filter=lfs diff=lfs merge=lfs -text
 models/starling-lm-7b-alpha.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+cuda_12.4.0_550.54.14_linux.run filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -2,6 +2,42 @@
 FROM ubuntu:22.04 as cuda-setup
 
 
+ARG DEBIAN_FRONTEND=noninteractive
+
+# Install necessary libraries including libxml2
+RUN apt-get update && \
+    apt-get install -y gcc libxml2 && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+COPY cuda_12.4.0_550.54.14_linux.run .
+
+# Install wget, download cuda-toolkit and run
+RUN chmod +x cuda_12.4.0_550.54.14_linux.run && \
+    ./cuda_12.4.0_550.54.14_linux.run --silent --toolkit --override
+
+# Second Stage: Copy necessary CUDA directories install flash-attn
+FROM ubuntu:22.04 as base-layer
+
+# Copy the CUDA toolkit from the first stage
+COPY --from=cuda-setup /usr/local/cuda-12.4 /usr/local/cuda-12.4
+
+# Set environment variables to enable CUDA commands
+ENV PATH=/usr/local/cuda-12.4/bin:${PATH}
+ENV LD_LIBRARY_PATH=/usr/local/cuda-12.4/lib64:${LD_LIBRARY_PATH}
+
+# Install Python, pip, and virtualenv
+RUN apt-get update && \ 
+    apt-get install -y python3 python3-pip python3-venv git && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# Create a virtual environment and install dependencies
+RUN python3 -m venv /venv
+ENV PATH="/venv/bin:$PATH"
+FROM ubuntu:22.04 as cuda-setup
+
+
 ARG DEBIAN_FRONTEND=noninteractive
 
 # Install necessary libraries including libxml2
@@ -38,10 +74,13 @@ ENV PATH="/venv/bin:$PATH"
 
 # Llama.cpp requires the ENV variable be set to signal the CUDA build and be built with the CMAKE variables from pip for python use
 ENV LLAMA_CUBLAS=1
+RUN pip install --no-cache-dir torch packaging wheel && \
+    pip install flash-attn && \
 RUN pip install --no-cache-dir torch packaging wheel && \
     pip install flash-attn && \
     pip install gradio && \
     CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama_cpp_python==0.2.55 && \
+    CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama_cpp_python==0.2.55 && \
     pip install pillow && \ 
     pip install diffusers && \
     pip install accelerate && \
@@ -60,6 +99,11 @@ ENV LD_LIBRARY_PATH=/usr/local/cuda-12.4/lib64:${LD_LIBRARY_PATH}
 ENV LLAMA_CPP_LIB=/venv/lib/python3.10/site-packages/llama_cpp/libllama.so
 ENV VIRTUAL_ENV=/venv
 
+# Install Python and create a user
+RUN apt-get update && apt-get install -y python3 python3-venv && apt-get clean && rm -rf /var/lib/apt/lists/* && \
+    useradd -m -u 1000 user
+    
+
 # Install Python and create a user
 RUN apt-get update && apt-get install -y python3 python3-venv && apt-get clean && rm -rf /var/lib/apt/lists/* && \
     useradd -m -u 1000 user
@@ -67,6 +111,8 @@ RUN apt-get update && apt-get install -y python3 python3-venv && apt-get clean &
 ENV PATH="$VIRTUAL_ENV/bin:$PATH"
 # Set working directory and user
 COPY . /home/user/app
+# Set working directory and user
+COPY . /home/user/app
 WORKDIR /home/user/app
 RUN chown -R user:user /home/user/app/ && \
     mkdir -p /home/user/app/output && \