mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-15 14:43:48 +00:00
007efa6eb5
# What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> The purpose of this PR is to replace the Llama Stack's default embedding model by nomic-embed-text-v1.5. These are the key reasons why Llama Stack community decided to switch from all-MiniLM-L6-v2 to nomic-embed-text-v1.5: 1. The training data for [all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2#training-data) includes a lot of data sets with various licensing terms, so it is tricky to know when/whether it is appropriate to use this model for commercial applications. 2. The model is not particularly competitive on major benchmarks. For example, if you look at the [MTEB Leaderboard](https://huggingface.co/spaces/mteb/leaderboard) and click on Miscellaneous/BEIR to see English information retrieval accuracy, you see that the top of the leaderboard is dominated by enormous models but also that there are many, many models of relatively modest size whith much higher Retrieval scores. If you want to look closely at the data, I recommend clicking "Download Table" because it is easier to browse that way. More discussion info can be founded [here](https://github.com/llamastack/llama-stack/issues/2418) <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> Closes #2418 ## Test Plan <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> 1. Run `./scripts/unit-tests.sh` 2. Integration tests via CI wokrflow --------- Signed-off-by: Sébastien Han <seb@redhat.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com> Co-authored-by: Sébastien Han <seb@redhat.com>
14 lines
491 B
Docker
14 lines
491 B
Docker
# Containerfile used to build our Ollama image with vision model to run tests in CI
|
|
#
|
|
# podman build --platform linux/amd64 -f ./ollama-with-vision-model.containerfile -t ollama-with-vision-model .
|
|
#
|
|
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-vision:11b && \
|
|
ollama pull nomic-embed-text:v1.5
|
|
|
|
# Set the entrypoint to start ollama serve
|
|
ENTRYPOINT ["ollama", "serve"]
|