forked from phoenix-oss/llama-stack-mirror
# What does this PR do? adds a new method build_model_alias_with_just_llama_model which is needed for cases like ollama's quantized models which do not really have a repo in hf and an entry in SKU list. ## Test Plan pytest -v -s -m "ollama" llama_stack/providers/tests/inference/test_text_inference.py --------- Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com> |
||
---|---|---|
.. | ||
agents | ||
datasetio/huggingface | ||
inference | ||
memory | ||
safety | ||
telemetry | ||
__init__.py |