llama2 #130
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: llama2 | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.head_ref || github.ref }} | |
| cancel-in-progress: true | |
| on: | |
| workflow_dispatch: | |
| inputs: | |
| logLevel: | |
| description: 'Log level' | |
| required: true | |
| default: 'info' | |
| push: | |
| branches: | |
| - "main" | |
| schedule: | |
| - cron: "0 0 */1 * *" | |
| jobs: | |
| preview-feature: | |
| runs-on: ubuntu-latest | |
| steps: | |
| - name: Manually update GitHub's containerd | |
| run: | | |
| wget https://github.com/containerd/containerd/releases/download/v1.7.5/containerd-1.7.5-linux-amd64.tar.gz | |
| sudo tar Czxvf /usr containerd-1.7.5-linux-amd64.tar.gz | |
| sudo systemctl restart containerd | |
| - name: Set up Docker | |
| uses: crazy-max/ghaction-setup-docker@v2 | |
| with: | |
| daemon-config: | | |
| { | |
| "debug": true, | |
| "features": { | |
| "containerd-snapshotter": true | |
| } | |
| } | |
| - name: Fetch Llama-2-7B-GGUF model | |
| run: curl -LO https://huggingface.co/TheBloke/Llama-2-7B-GGUF/resolve/main/llama-2-7b.Q5_K_M.gguf | |
| - name: Fetch WASI-NN GGML with LLAMA2 example image | |
| run: sudo ctr image pull ghcr.io/second-state/runwasi-demo:llama-simple | |
| - name: Install WASI-NN GGML plugin (preview) | |
| run: | | |
| sudo ctr content fetch ghcr.io/second-state/runwasi-wasmedge-plugin:allinone.wasi_nn-ggml | |
| sudo ctr install ghcr.io/second-state/runwasi-wasmedge-plugin:allinone.wasi_nn-ggml -l -r | |
| - name: Run WASI-NN GGML with LLAMA2 example (preview) through containerd | |
| run: | | |
| sudo ctr run --rm --runtime=io.containerd.wasmedge.v1 \ | |
| --mount type=bind,src=/opt/containerd/lib,dst=/opt/containerd/lib,options=bind:ro \ | |
| --mount type=bind,src=$PWD,dst=/resource,options=bind:ro \ | |
| --env WASMEDGE_PLUGIN_PATH=/opt/containerd/lib \ | |
| --env WASMEDGE_WASINN_PRELOAD=default:GGML:CPU:/resource/llama-2-7b.Q5_K_M.gguf \ | |
| ghcr.io/second-state/runwasi-demo:llama-simple testggml /app.wasm \ | |
| --model-alias default --ctx-size 4096 --n-predict 128 --log-enable --stream-stdout \ | |
| --prompt 'Robert Oppenheimer most important achievement is ' | |
| - name: Run WASI-NN GGML with LLAMA2 example (preview) through docker | |
| run: | | |
| docker run --rm --runtime=io.containerd.wasmedge.v1 --platform wasi/wasm \ | |
| -v /opt/containerd/lib:/opt/containerd/lib \ | |
| -v $PWD:/resource \ | |
| --env WASMEDGE_PLUGIN_PATH=/opt/containerd/lib \ | |
| --env WASMEDGE_WASINN_PRELOAD=default:GGML:CPU:/resource/llama-2-7b.Q5_K_M.gguf \ | |
| ghcr.io/second-state/runwasi-demo:llama-simple \ | |
| --model-alias default --ctx-size 4096 --n-predict 128 --log-enable --stream-stdout \ | |
| --prompt 'Robert Oppenheimer most important achievement is ' |