From bbea9bccf1f92f23305dcacd12c4ed33b5c10631 Mon Sep 17 00:00:00 2001 From: Connor Hack Date: Mon, 25 Nov 2024 09:20:27 -0800 Subject: [PATCH] Revert provider / inference config back to mainline --- .../providers/inline/inference/meta_reference/inference.py | 4 ++-- llama_stack/templates/meta-reference-gpu/meta_reference.py | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/llama_stack/providers/inline/inference/meta_reference/inference.py b/llama_stack/providers/inline/inference/meta_reference/inference.py index 6743ca822..07fd4af44 100644 --- a/llama_stack/providers/inline/inference/meta_reference/inference.py +++ b/llama_stack/providers/inline/inference/meta_reference/inference.py @@ -36,8 +36,6 @@ class MetaReferenceInferenceImpl(Inference, ModelRegistryHelper, ModelsProtocolP def __init__(self, config: MetaReferenceInferenceConfig) -> None: self.config = config model = resolve_model(config.model) - if model is None: - raise RuntimeError(f"Unknown model: {config.model}, Run `llama model list`") ModelRegistryHelper.__init__( self, [ @@ -47,6 +45,8 @@ class MetaReferenceInferenceImpl(Inference, ModelRegistryHelper, ModelsProtocolP ) ], ) + if model is None: + raise RuntimeError(f"Unknown model: {config.model}, Run `llama model list`") self.model = model # verify that the checkpoint actually is for this model lol diff --git a/llama_stack/templates/meta-reference-gpu/meta_reference.py b/llama_stack/templates/meta-reference-gpu/meta_reference.py index 2408ef972..f254bc920 100644 --- a/llama_stack/templates/meta-reference-gpu/meta_reference.py +++ b/llama_stack/templates/meta-reference-gpu/meta_reference.py @@ -81,7 +81,7 @@ def get_distribution_template() -> DistributionTemplate: "Port for the Llama Stack distribution server", ), "INFERENCE_MODEL": ( - "meta-llama/Llama3.2-3B-Instruct", + "meta-llama/Llama-3.2-3B-Instruct", "Inference model loaded into the Meta Reference server", ), "INFERENCE_CHECKPOINT_DIR": (