[CI] ggml: add llama2 7b chat examples #199
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: ggml llama2 examples | |
| on: | |
| schedule: | |
| - cron: "0 0 * * *" | |
| workflow_dispatch: | |
| inputs: | |
| logLevel: | |
| description: 'Log level' | |
| required: true | |
| default: 'info' | |
| push: | |
| branches: [ '*' ] | |
| paths: | |
| - ".github/workflows/llama.yml" | |
| - "wasmedge-ggml-llama-interactive/**" | |
| pull_request: | |
| branches: [ '*' ] | |
| paths: | |
| - ".github/workflows/llama.yml" | |
| - "wasmedge-ggml-llama-interactive/**" | |
| jobs: | |
| ubuntu: | |
| runs-on: ubuntu-20.04 | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: Install apt-get packages | |
| run: | | |
| echo RESET grub-efi/install_devices | sudo debconf-communicate grub-pc | |
| sudo ACCEPT_EULA=Y apt-get update | |
| sudo ACCEPT_EULA=Y apt-get upgrade | |
| sudo apt-get install wget git curl software-properties-common build-essential libopenblas-dev | |
| - name: Install Rust target for wasm | |
| run: | | |
| rustup target add wasm32-wasi | |
| - name: Install WasmEdge + WASI-NN + GGML | |
| run: | | |
| VERSION=0.13.5 | |
| curl -sSf https://raw.githubusercontent.com/WasmEdge/WasmEdge/master/utils/install.sh | sudo bash -s -- -v $VERSION --plugins wasi_nn-ggml -p /usr/local | |
| - name: Tiny Llama | |
| run: | | |
| cd wasmedge-ggml-llama-interactive | |
| curl -LO https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v0.3-GGUF/resolve/main/tinyllama-1.1b-chat-v0.3.Q5_K_M.gguf | |
| cargo build --target wasm32-wasi --release | |
| wasmedge --dir .:. \ | |
| --nn-preload default:GGML:AUTO:tinyllama-1.1b-chat-v0.3.Q5_K_M.gguf \ | |
| --env enable_log=true \ | |
| --env ctx_size=4096 \ | |
| --env stream_stdout=true \ | |
| --env n_gpu_layers=0 \ | |
| target/wasm32-wasi/release/wasmedge-ggml-llama-interactive.wasm \ | |
| default \ | |
| '<|im_start|>system\nYou are an AI assistant<|im_end|>\n<|im_start|>user\nWhere is the capital of Japan?<|im_end|>\n<|im_start|>assistant' | |
| - name: llama2 7b | |
| run: | | |
| cd wasmedge-ggml-llama-interactive | |
| curl -LO https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF/resolve/main/llama-2-7b-chat.Q5_K_M.gguf | |
| cargo build --target wasm32-wasi --release | |
| wasmedge --dir .:. \ | |
| --nn-preload default:GGML:AUTO:llama-2-7b-chat.Q5_K_M.gguf \ | |
| --env enable_log=true \ | |
| --env ctx_size=4096 \ | |
| --env stream_stdout=true \ | |
| --env n_gpu_layers=0 \ | |
| target/wasm32-wasi/release/wasmedge-ggml-llama-interactive.wasm \ | |
| default \ | |
| '[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you do not know the answer to a question, please do not share false information.\n<</SYS>>\nWhat is the capital of Japan?[/INST]' | |
| macos: | |
| strategy: | |
| matrix: | |
| include: | |
| - name: MacOS-13 | |
| host_runner: macos-13 | |
| - name: MacOS-14 | |
| host_runner: macos-14 | |
| name: ${{ matrix.name }} | |
| runs-on: ${{ matrix.host_runner }} | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - uses: actions-rust-lang/setup-rust-toolchain@v1 | |
| - name: Install Rust target for wasm | |
| run: | | |
| rustup target add wasm32-wasi | |
| - name: Install WasmEdge + WASI-NN + GGML | |
| run: | | |
| VERSION=0.13.5 | |
| curl -sSf https://raw.githubusercontent.com/WasmEdge/WasmEdge/master/utils/install.sh | sudo bash -s -- -v $VERSION --plugins wasi_nn-ggml -p /usr/local | |
| - name: Tiny Llama | |
| run: | | |
| cd wasmedge-ggml-llama-interactive | |
| curl -LO https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v0.3-GGUF/resolve/main/tinyllama-1.1b-chat-v0.3.Q5_K_M.gguf | |
| cargo build --target wasm32-wasi --release | |
| wasmedge --dir .:. \ | |
| --nn-preload default:GGML:AUTO:tinyllama-1.1b-chat-v0.3.Q5_K_M.gguf \ | |
| --env enable_log=true \ | |
| --env ctx_size=4096 \ | |
| --env stream_stdout=true \ | |
| --env n_gpu_layers=0 \ | |
| target/wasm32-wasi/release/wasmedge-ggml-llama-interactive.wasm \ | |
| default \ | |
| '<|im_start|>system\nYou are an AI assistant<|im_end|>\n<|im_start|>user\nWhere is the capital of Japan?<|im_end|>\n<|im_start|>assistant' | |
| - name: llama2 7b | |
| run: | | |
| cd wasmedge-ggml-llama-interactive | |
| curl -LO https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF/resolve/main/llama-2-7b-chat.Q5_K_M.gguf | |
| cargo build --target wasm32-wasi --release | |
| wasmedge --dir .:. \ | |
| --nn-preload default:GGML:AUTO:llama-2-7b-chat.Q5_K_M.gguf \ | |
| --env enable_log=true \ | |
| --env ctx_size=4096 \ | |
| --env stream_stdout=true \ | |
| --env n_gpu_layers=0 \ | |
| target/wasm32-wasi/release/wasmedge-ggml-llama-interactive.wasm \ | |
| default \ | |
| '[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you do not know the answer to a question, please do not share false information.\n<</SYS>>\nWhat is the capital of Japan?[/INST]' |