phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-25 21:08:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: set proper name for embedding all-minilm:l6-v2 model

Browse source 
- 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>
This commit is contained in:
Wen Zhou 2025-07-04 15:53:53 +02:00
parent ea966565f6
commit 214b1fe1ae
4 changed files with 5 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/remote/inference/ollama/models.py
View file

@ -84,7 +84,7 @@ MODEL_ENTRIES = [
CoreModelId.llama_guard_3_1b.value,
),
ProviderModelEntry(
provider_model_id="all-minilm:latest",
provider_model_id="all-minilm:l6-v2",
aliases=["all-minilm"],
model_type=ModelType.embedding,
metadata={