Docker build of Alpaca.cpp

[ksylvan]

Build and Run Alpaca in Docker

This bypasses the need to install and maintain local toolchains on your machine to run the optimized Alpaca models locally
and further increases access and availability of these models.

Here's the build on my Macbook Air M2:

% make DOCKER_CLI=nerdctl docker                                        
I llama.cpp build info: 
I UNAME_S:  Darwin
I UNAME_P:  arm
I UNAME_M:  arm64
I CFLAGS:   -I.              -O3 -DNDEBUG -std=c11   -fPIC -pthread -DGGML_USE_ACCELERATE
I CXXFLAGS: -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -pthread
I LDFLAGS:   -framework Accelerate
I CC:       Apple clang version 14.0.3 (clang-1403.0.22.14.1)
I CXX:      Apple clang version 14.0.3 (clang-1403.0.22.14.1)

nerdctl build --build-arg UNAME_P=arm \
                --build-arg UNAME_M=arm64 -t alpaca.cpp .
[+] Building 13.0s (11/11)                                                                                                                                                         
[+] Building 13.1s (11/11) FINISHED                                                                                                                                                
 => [internal] load .dockerignore                                                                                                                                             0.0s
 => => transferring context: 79B                                                                                                                                              0.0s
 => [internal] load build definition from Dockerfile                                                                                                                          0.0s
 => => transferring dockerfile: 392B                                                                                                                                          0.0s
 => [internal] load metadata for docker.io/library/gcc:latest                                                                                                                 7.7s
 => [auth] library/gcc:pull token for registry-1.docker.io                                                                                                                    0.0s
 => [internal] load build context                                                                                                                                             0.0s
 => => transferring context: 432B                                                                                                                                             0.0s
 => [build 1/4] FROM docker.io/library/gcc@sha256:b12d1e7c37e101fd76848570b81352fe9546dd1caad84501d58aecd8d6c21cd8                                                            0.0s
 => => resolve docker.io/library/gcc@sha256:b12d1e7c37e101fd76848570b81352fe9546dd1caad84501d58aecd8d6c21cd8                                                                  0.0s
 => CACHED [build 2/4] WORKDIR /usr/src                                                                                                                                       0.0s
 => CACHED [build 3/4] COPY . /usr/src                                                                                                                                        0.0s
 => CACHED [build 4/4] RUN make UNAME_M=arm64 UNAME_P=arm                                                                                                                     0.0s
 => CACHED [stage-1 2/2] COPY --from=build /usr/src/chat /usr/src/quantize /usr/local/bin                                                                                     0.0s
 => exporting to docker image format                                                                                                                                          5.1s
 => => exporting layers                                                                                                                                                       0.0s
 => => exporting manifest sha256:9008dd57f2d3fa021178e7e670060a5bf9d6d5dd3eb5f65b206d60a95d73c247                                                                             0.0s
 => => exporting config sha256:145343d796357dce7b0ee939f5a103213debaa50f971841237f325db7658b177                                                                               0.0s
 => => sending tarball                                                                                                                                                        5.1s
Loaded image: docker.io/library/alpaca.cpp:latest

And the run looks like this (as in the README, this is not sped up):