[Docs] ggml: add README for the embedding example with CI job (#114) #319
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/**" | |
| pull_request: | |
| branches: [ '*' ] | |
| paths: | |
| - ".github/workflows/llama.yml" | |
| - "wasmedge-ggml/**" | |
| jobs: | |
| build: | |
| strategy: | |
| matrix: | |
| runner: [ubuntu-20.04, macos-13, macos-m1] | |
| job: | |
| - name: "Tiny Llama" | |
| run: | | |
| test -f ~/.wasmedge/env && source ~/.wasmedge/env | |
| cd wasmedge-ggml/llama | |
| 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 | |
| time wasmedge --dir .:. \ | |
| --env n_gpu_layers="$NGL" \ | |
| --nn-preload default:GGML:AUTO:tinyllama-1.1b-chat-v0.3.Q5_K_M.gguf \ | |
| target/wasm32-wasi/release/wasmedge-ggml-llama.wasm \ | |
| default \ | |
| $'<|im_start|>system\nYou are an AI assistant<|im_end|>\n<|im_start|>user\nWhere is the capital of Japan?<|im_end|>\n<|im_start|>assistant' | |
| - name: Gemma 2B | |
| run: | | |
| test -f ~/.wasmedge/env && source ~/.wasmedge/env | |
| cd wasmedge-ggml/gemma | |
| curl -LO https://huggingface.co/second-state/Gemma-2b-it-GGUF/resolve/main/gemma-2b-it-Q5_K_M.gguf | |
| cargo build --target wasm32-wasi --release | |
| time wasmedge --dir .:. \ | |
| --env n_gpu_layers="$NGL" \ | |
| --nn-preload default:GGML:AUTO:gemma-2b-it-Q5_K_M.gguf \ | |
| target/wasm32-wasi/release/wasmedge-ggml-gemma.wasm \ | |
| default \ | |
| '<start_of_turn>user Where is the capital of Japan? <end_of_turn><start_of_turn>model' | |
| - name: Llava v1.5 7B | |
| run: | | |
| test -f ~/.wasmedge/env && source ~/.wasmedge/env | |
| cd wasmedge-ggml/llava | |
| curl -LO https://huggingface.co/mys/ggml_llava-v1.5-7b/resolve/main/ggml-model-q5_k.gguf | |
| curl -LO https://huggingface.co/mys/ggml_llava-v1.5-7b/resolve/main/mmproj-model-f16.gguf | |
| curl -LO https://llava-vl.github.io/static/images/monalisa.jpg | |
| cargo build --target wasm32-wasi --release | |
| time wasmedge --dir .:. \ | |
| --env mmproj=mmproj-model-f16.gguf \ | |
| --env image=monalisa.jpg \ | |
| --env n_gpu_layers="$NGL" \ | |
| --nn-preload default:GGML:AUTO:ggml-model-q5_k.gguf \ | |
| target/wasm32-wasi/release/wasmedge-ggml-llava.wasm \ | |
| default \ | |
| $'You are a helpful, respectful and honest assistant. Always answer as short as possible, while being safe.\nUSER:<image>\nDo you know who drew this painting?\nASSISTANT:' | |
| - name: Llava v1.6 7B | |
| run: | | |
| test -f ~/.wasmedge/env && source ~/.wasmedge/env | |
| cd wasmedge-ggml/llava | |
| curl -LO https://huggingface.co/cmp-nct/llava-1.6-gguf/resolve/main/vicuna-7b-q5_k.gguf | |
| curl -LO https://huggingface.co/cmp-nct/llava-1.6-gguf/resolve/main/mmproj-vicuna7b-f16.gguf | |
| curl -LO https://llava-vl.github.io/static/images/monalisa.jpg | |
| cargo build --target wasm32-wasi --release | |
| time wasmedge --dir .:. \ | |
| --env mmproj=mmproj-vicuna7b-f16.gguf \ | |
| --env image=monalisa.jpg \ | |
| --env ctx_size=4096 \ | |
| --env n_gpu_layers="$NGL" \ | |
| --nn-preload default:GGML:AUTO:vicuna-7b-q5_k.gguf \ | |
| target/wasm32-wasi/release/wasmedge-ggml-llava.wasm \ | |
| default \ | |
| $'You are a helpful, respectful and honest assistant. Always answer as short as possible, while being safe.\nUSER:<image>\nDo you know who drew this painting?\nASSISTANT:' | |
| - name: Llama2 7B | |
| run: | | |
| test -f ~/.wasmedge/env && source ~/.wasmedge/env | |
| cd wasmedge-ggml/llama | |
| curl -LO https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF/resolve/main/llama-2-7b-chat.Q5_K_M.gguf | |
| cargo build --target wasm32-wasi --release | |
| time wasmedge --dir .:. \ | |
| --env n_gpu_layers="$NGL" \ | |
| --nn-preload default:GGML:AUTO:llama-2-7b-chat.Q5_K_M.gguf \ | |
| target/wasm32-wasi/release/wasmedge-ggml-llama.wasm \ | |
| default \ | |
| $'[INST] <<SYS>>\nYou are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you do not know the answer to a question, please do not share false information.\n<</SYS>>\nWhat is the capital of Japan?[/INST]' | |
| - name: StarCoder 2 7B | |
| run: | | |
| test -f ~/.wasmedge/env && source ~/.wasmedge/env | |
| cd wasmedge-ggml/basic | |
| curl -LO https://huggingface.co/second-state/StarCoder2-7B-GGUF/resolve/main/starcoder2-7b-Q5_K_M.gguf | |
| cargo build --target wasm32-wasi --release | |
| time wasmedge --dir .:. \ | |
| --env n_gpu_layers="$NGL" \ | |
| --env n_predict=100 \ | |
| --nn-preload default:GGML:AUTO:starcoder2-7b-Q5_K_M.gguf \ | |
| target/wasm32-wasi/release/wasmedge-ggml-basic.wasm \ | |
| default \ | |
| 'def print_hello_world():' | |
| - name: Multiple Models Example | |
| run: | | |
| test -f ~/.wasmedge/env && source ~/.wasmedge/env | |
| cd wasmedge-ggml/multimodel | |
| curl -LO https://huggingface.co/second-state/Llama-2-7B-Chat-GGUF/resolve/main/llama-2-7b-chat.Q5_K_M.gguf | |
| curl -LO https://huggingface.co/cmp-nct/llava-1.6-gguf/resolve/main/vicuna-7b-q5_k.gguf | |
| curl -LO https://huggingface.co/cmp-nct/llava-1.6-gguf/resolve/main/mmproj-vicuna7b-f16.gguf | |
| curl -LO https://llava-vl.github.io/static/images/monalisa.jpg | |
| cargo build --target wasm32-wasi --release | |
| time wasmedge --dir .:. \ | |
| --env n_gpu_layers="$NGL" \ | |
| --env image=monalisa.jpg \ | |
| --env mmproj=mmproj-vicuna7b-f16.gguf \ | |
| --nn-preload llama2:GGML:AUTO:llama-2-7b-chat.Q5_K_M.gguf \ | |
| --nn-preload llava:GGML:AUTO:vicuna-7b-q5_k.gguf \ | |
| target/wasm32-wasi/release/wasmedge-ggml-multimodel.wasm \ | |
| 'describe this picture please' | |
| - name: Embedding Example | |
| run: | | |
| test -f ~/.wasmedge/env && source ~/.wasmedge/env | |
| cd wasmedge-ggml/embedding | |
| curl -LO https://huggingface.co/second-state/All-MiniLM-L6-v2-Embedding-GGUF/resolve/main/all-MiniLM-L6-v2-ggml-model-f16.gguf | |
| cargo build --target wasm32-wasi --release | |
| time wasmedge --dir .:. \ | |
| --nn-preload default:GGML:AUTO:all-MiniLM-L6-v2-ggml-model-f16.gguf \ | |
| target/wasm32-wasi/release/wasmedge-ggml-llama-embedding.wasm \ | |
| default \ | |
| 'hello world' | |
| - name: Build llama-stream | |
| run: | | |
| cd wasmedge-ggml/llama-stream | |
| cargo build --target wasm32-wasi --release | |
| - name: Build chatml | |
| run: | | |
| cd wasmedge-ggml/chatml | |
| cargo build --target wasm32-wasi --release | |
| - name: Build llava-base64-stream | |
| run: | | |
| cd wasmedge-ggml/llava-base64-stream | |
| cargo build --target wasm32-wasi --release | |
| include: | |
| - runner: macos-m1 | |
| ngl: 100 | |
| name: ${{ matrix.runner }} - ${{ matrix.job.name }} | |
| runs-on: ${{ matrix.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 | bash -s -- -v $VERSION --plugins wasi_nn-ggml | |
| - name: Set environment variable | |
| run: echo "NGL=${{ matrix.ngl || 0 }}" >> $GITHUB_ENV | |
| - name: ${{ matrix.job.name }} | |
| run: ${{ matrix.job.run }} |