mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-24 22:10:01 +00:00
214b1fe1ae
- we are using all-minilm:l6-v2 but the model we download from ollama is all-minilm:latest - even currently they are exactly the same model but if l12-v2 is updated, "latest" might not still valid. - the only change in this PR is pin the model from ollama Signed-off-by: Wen Zhou <wenzhou@redhat.com>
13 lines
450 B
Docker
13 lines
450 B
Docker
# Containerfile used to build our all in one ollama image to run tests in CI
|
|
# podman build --platform linux/amd64 -f Containerfile -t ollama-with-models .
|
|
#
|
|
FROM --platform=linux/amd64 ollama/ollama:latest
|
|
|
|
# Start ollama and pull models in a single layer
|
|
RUN ollama serve & \
|
|
sleep 5 && \
|
|
ollama pull llama3.2:3b-instruct-fp16 && \
|
|
ollama pull all-minilm:l6-v2
|
|
|
|
# Set the entrypoint to start ollama serve
|
|
ENTRYPOINT ["ollama", "serve"]
|