feat: add last version LLAMA

.dockerignore

@@ -1,4 +1,11 @@
 *
 !*.py
+!*.txt
+!*.html
+!*.sh
 !requirements.txt
 !SOURCE_DOCUMENTS
+!static
+!websocket
+
+

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -1,21 +1,37 @@
 # syntax=docker/dockerfile:1
 # Build as `docker build . -t localgpt`, requires BuildKit.
 # Run as `docker run -it --mount src="$HOME/.cache",target=/root/.cache,type=bind --gpus=all localgpt`, requires Nvidia container toolkit.
+FROM nvidia/cuda:12.1.1-devel-ubuntu22.04
+
+RUN apt-get update && apt-get upgrade -y \
+    && apt-get install -y git build-essential libpq-dev gcc \
+    wget ocl-icd-opencl-dev opencl-headers clinfo \
+    libclblast-dev libopenblas-dev software-properties-common \
+    g++-11 make python3 python-is-python3 pip redis \
+    && mkdir -p /etc/OpenCL/vendors && echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.icd
 
-FROM nvidia/cuda:11.7.1-runtime-ubuntu22.04
-RUN apt-get update && apt-get install -y software-properties-common
-RUN apt-get install -y g++-11 make python3 python-is-python3 pip
-# only copy what's needed at every step to optimize layer cache
-COPY ./requirements.txt .
-# use BuildKit cache mount to drastically reduce redownloading from pip on repeated builds
-RUN --mount=type=cache,target=/root/.cache CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install --timeout 100 -r requirements.txt llama-cpp-python==0.1.83
-COPY SOURCE_DOCUMENTS ./SOURCE_DOCUMENTS
-COPY ingest.py constants.py ./
-# Docker BuildKit does not support GPU during *docker build* time right now, only during *docker run*.
-# See <https://github.com/moby/buildkit/issues/1436>.
-# If this changes in the future you can `docker build --build-arg device_type=cuda  . -t localgpt` (+GPU argument to be determined).
-ARG device_type=cpu
-RUN --mount=type=cache,target=/root/.cache python ingest.py --device_type $device_type
 COPY . .
-ENV device_type=cuda
-CMD python run_localGPT.py --device_type $device_type
+
+# setting build related env vars
+ENV CUDA_DOCKER_ARCH=all
+ENV LLAMA_CUBLAS=1
+
+# Install depencencies
+RUN python -m pip install --upgrade pip pytest cmake \
+    scikit-build setuptools fastapi uvicorn sse-starlette \
+    pydantic-settings starlette-context gradio huggingface_hub hf_transfer
+
+RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
+RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 PIP_ROOT_USER_ACTION=ignore pip install --ignore-installed --timeout 100 -r requirements.txt
+RUN pip install uvicorn
+
+RUN useradd -m -u 1000 user
+USER user
+
+WORKDIR $HOME/app
+
+COPY --chown=user . $HOME/app
+
+RUN chmod +x ./run.sh
+
+CMD ["sh", "run.sh"]