phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 15:49:49 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add embedding model by default

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-12-12 14:46:51 -08:00
parent 2a9b13dd52
commit 2f88006bd0
43 changed files with 446 additions and 85 deletions
Download patch file Download diff file Expand all files Collapse all files

23
llama_stack/templates/cerebras/cerebras.py
View file

@ -8,10 +8,14 @@ from pathlib import Path
from llama_models.sku_list import all_registered_models
from llama_stack.apis.models.models import ModelType
from llama_stack.distribution.datatypes import ModelInput, Provider, ShieldInput
from llama_stack.providers.inline.inference.sentence_transformers import (
SentenceTransformersInferenceConfig,
)
from llama_stack.providers.remote.inference.cerebras import CerebrasImplConfig
from llama_stack.providers.remote.inference.cerebras.cerebras import model_aliases
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@ -29,6 +33,11 @@ def get_distribution_template() -> DistributionTemplate:
provider_type="remote::cerebras",
config=CerebrasImplConfig.sample_run_config(),
)
embedding_provider = Provider(
provider_id="sentence-transformers",
provider_type="inline::sentence-transformers",
config=SentenceTransformersInferenceConfig.sample_run_config(),
)
core_model_to_hf_repo = {
m.descriptor(): m.huggingface_repo for m in all_registered_models()
@ -40,6 +49,14 @@ def get_distribution_template() -> DistributionTemplate:
)
for m in model_aliases
]
embedding_model = ModelInput(
model_id="all-MiniLM-L6-v2",
provider_id="sentence-transformers",
model_type=ModelType.embedding,
metadata={
"embedding_dim": 384,
},
)
return DistributionTemplate(
name="cerebras",
@ -52,9 +69,9 @@ def get_distribution_template() -> DistributionTemplate:
run_configs={
"run.yaml": RunConfigSettings(
provider_overrides={
"inference": [inference_provider],
"inference": [inference_provider, embedding_provider],
},
default_models=default_models,
default_models=default_models + [embedding_model],
default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
),
},