llama-stack-mirror/.github/actions/setup-ollama/action.yml
2025-05-01 11:35:12 +01:00

26 lines
937 B
YAML

name: Setup Ollama
description: Start Ollama and cache model
inputs:
models:
description: Comma-separated list of models to pull
default: "llama3.2:3b-instruct-fp16,all-minilm:latest"
runs:
using: "composite"
steps:
- name: Install and start Ollama
shell: bash
run: |
# the ollama installer also starts the ollama service
curl -fsSL https://ollama.com/install.sh | sh
# Do NOT cache models - pulling the cache is actually slower than just pulling the model.
# It takes ~45 seconds to pull the models from the cache and unpack it, but only 30 seconds to
# pull them directly.
# Maybe this is because the cache is being pulled at the same time by all the matrix jobs?
- name: Pull requested models
if: inputs.models != ''
shell: bash
run: |
for model in $(echo "${{ inputs.models }}" | tr ',' ' '); do
ollama pull "$model"
done