Revert "🚀 Dockerize llamacpp (antimatter15#132)"

This reverts commit 2af23d3.

.github/workflows/build.yml

@@ -17,7 +17,7 @@ env:
  BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
 
 jobs:
- ubuntu-latest-make:
+ ubuntu-latest:
  runs-on: ubuntu-latest
 
  steps:
@@ -36,27 +36,8 @@ jobs:
  run: |
  make
 
- ubuntu-latest-cmake:
- runs-on: ubuntu-latest
-
- steps:
- - name: Clone
- uses: actions/checkout@v1
-
- - name: Dependencies
- run: |
- sudo apt-get update
- sudo apt-get install build-essential
-
- - name: Build
- run: |
- mkdir build
- cd build
- cmake ..
- cmake --build . --config Release
-
- macOS-latest-make:
- runs-on: macos-latest
+ macOS-latest:
+ runs-on: macOS-latest
 
  steps:
  - name: Clone
@@ -73,25 +54,7 @@ jobs:
  run: |
  make
 
- macOS-latest-cmake:
- runs-on: macOS-latest
-
- steps:
- - name: Clone
- uses: actions/checkout@v1
-
- - name: Dependencies
- run: |
- brew update
-
- - name: Build
- run: |
- mkdir build
- cd build
- cmake ..
- cmake --build . --config Release
-
- windows-latest-cmake:
+ windows-latest:
  runs-on: windows-latest
 
  steps:

README.md

@@ -32,7 +32,6 @@ Supported platforms:
 - [X] Mac OS
 - [X] Linux
 - [X] Windows (via CMake)
-- [X] Docker
 
 ---
 
@@ -237,38 +236,6 @@ Finally, copy the `llama` binary and the model files to your device storage. Her
 
 https://user-images.githubusercontent.com/271616/225014776-1d567049-ad71-4ef2-b050-55b0b3b9274c.mp4
 
-### Docker
-
-#### Prerequisites
-* Docker must be installed and running on your system.
-* Create a folder to store big models & intermediate files (in ex. im using /llama/models)
-
-#### Images
-We have two Docker images available for this project:
-
-1. `ghcr.io/ggerganov/llama.cpp:full`: This image includes both the main executable file and the tools to convert LLaMA models into ggml and convert into 4-bit quantization.
-2. `ghcr.io/ggerganov/llama.cpp:light`: This image only includes the main executable file.
-
-#### Usage
-
-The easiest way to download the models, convert them to ggml and optimize them is with the --all-in-one command which includes the full docker image.
-
- ```bash
-docker run -v /llama/models:/models ghcr.io/ggerganov/llama.cpp:full --all-in-one "/models/" 7B
-```
-
-On complete, you are ready to play!
-
-```bash
-docker run -v /llama/models:/models ghcr.io/ggerganov/llama.cpp:full --run -m /models/7B/ggml-model-q4_0.bin -p "Building a website can be done in 10 simple steps:" -n 512
-```
-
-or with light image:
-
-```bash
-docker run -v /llama/models:/models ghcr.io/ggerganov/llama.cpp:light -m /models/7B/ggml-model-q4_0.bin -p "Building a website can be done in 10 simple steps:" -n 512
-```
-
 ## Limitations
 
 - We don't know yet how much the quantization affects the quality of the generated text