phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 21:49:48 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Ollama Setup

Browse source
This commit is contained in:
Aidan Do 2024-12-17 09:49:34 +11:00
parent 20383bfea5
commit 3b844afd00
3 changed files with 14 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -48,10 +48,10 @@ model_aliases = [
"llama3.1:8b-instruct-fp16",
CoreModelId.llama3_1_8b_instruct.value,
),
build_model_alias_with_just_provider_model_id(
"llama3.1:8b",
CoreModelId.llama3_1_8b_instruct.value,
),
# build_model_alias_with_just_provider_model_id(
# "llama3.1:8b",
# CoreModelId.llama3_1_8b_instruct.value,
# ),
build_model_alias(
"llama3.1:70b-instruct-fp16",
CoreModelId.llama3_1_70b_instruct.value,
@ -347,7 +347,7 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
)
return model
model = await self.register_helper.register_model(model)
models = await self.client.ps()
models = await self.client.list()
available_models = [m["model"] for m in models["models"]]
if model.provider_resource_id not in available_models:
raise ValueError(