phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-08 13:00:52 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Basic build and run succeeded

Browse source
This commit is contained in:
Ashwin Bharambe 2024-09-22 16:30:32 -07:00
parent 4d5ca49eed
commit 2ed65a47a4
9 changed files with 50 additions and 42 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/providers/impls/meta_reference/inference/config.py
View file

@ -6,17 +6,14 @@
from typing import Optional
from llama_models.datatypes import ModelFamily
from llama_models.schema_utils import json_schema_type
from llama_models.datatypes import * # noqa: F403
from llama_models.sku_list import all_registered_models, resolve_model
from llama_stack.apis.inference import * # noqa: F401, F403
from pydantic import BaseModel, Field, field_validator
from llama_stack.apis.inference import QuantizationConfig
@json_schema_type
class MetaReferenceImplConfig(BaseModel):
model: str = Field(
default="Meta-Llama3.1-8B-Instruct",
@ -34,6 +31,7 @@ class MetaReferenceImplConfig(BaseModel):
m.descriptor()
for m in all_registered_models()
if m.model_family == ModelFamily.llama3_1
or m.core_model_id == CoreModelId.llama_guard_3_8b
]
if model not in permitted_models:
model_list = "\n\t".join(permitted_models)

14
llama_stack/providers/registry/inference.py
View file

@ -32,10 +32,6 @@ def available_providers() -> List[ProviderSpec]:
adapter_id="ollama",
pip_packages=["ollama"],
module="llama_stack.providers.adapters.inference.ollama",
supported_model_ids=[
"Meta-Llama3.1-8B-Instruct",
"Meta-Llama3.1-70B-Instruct",
],
),
),
remote_provider_spec(
@ -56,11 +52,6 @@ def available_providers() -> List[ProviderSpec]:
],
module="llama_stack.providers.adapters.inference.fireworks",
config_class="llama_stack.providers.adapters.inference.fireworks.FireworksImplConfig",
supported_model_ids=[
"Meta-Llama3.1-8B-Instruct",
"Meta-Llama3.1-70B-Instruct",
"Meta-Llama3.1-405B-Instruct",
],
),
),
remote_provider_spec(
@ -73,11 +64,6 @@ def available_providers() -> List[ProviderSpec]:
module="llama_stack.providers.adapters.inference.together",
config_class="llama_stack.providers.adapters.inference.together.TogetherImplConfig",
header_extractor_class="llama_stack.providers.adapters.inference.together.TogetherHeaderExtractor",
supported_model_ids=[
"Meta-Llama3.1-8B-Instruct",
"Meta-Llama3.1-70B-Instruct",
"Meta-Llama3.1-405B-Instruct",
],
),
),
]