phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 09:42:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update Fireworks + Togther documentation

Browse source
This commit is contained in:
Ashwin Bharambe 2024-11-18 12:52:23 -08:00
parent 1ecaf2cb3c
commit a562668dcd
27 changed files with 879 additions and 445 deletions
Download patch file Download diff file Expand all files Collapse all files

9
llama_stack/providers/remote/inference/fireworks/config.py
View file

@ -4,7 +4,7 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from typing import Optional
from typing import Any, Dict, Optional
from llama_models.schema_utils import json_schema_type
from pydantic import BaseModel, Field
@ -20,3 +20,10 @@ class FireworksImplConfig(BaseModel):
default=None,
description="The Fireworks.ai API Key",
)
@classmethod
def sample_run_config(cls) -> Dict[str, Any]:
return {
"url": "https://api.fireworks.ai/inference",
"api_key": "${env.FIREWORKS_API_KEY}",
}

4
llama_stack/providers/remote/inference/fireworks/fireworks.py
View file

@ -35,7 +35,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
from .config import FireworksImplConfig
model_aliases = [
MODEL_ALIASES = [
build_model_alias(
"fireworks/llama-v3p1-8b-instruct",
CoreModelId.llama3_1_8b_instruct.value,
@ -79,7 +79,7 @@ class FireworksInferenceAdapter(
ModelRegistryHelper, Inference, NeedsRequestProviderData
):
def __init__(self, config: FireworksImplConfig) -> None:
ModelRegistryHelper.__init__(self, model_aliases)
ModelRegistryHelper.__init__(self, MODEL_ALIASES)
self.config = config
self.formatter = ChatFormat(Tokenizer.get_instance())

9
llama_stack/providers/remote/inference/together/config.py
View file

@ -4,7 +4,7 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from typing import Optional
from typing import Any, Dict, Optional
from llama_models.schema_utils import json_schema_type
from pydantic import BaseModel, Field
@ -20,3 +20,10 @@ class TogetherImplConfig(BaseModel):
default=None,
description="The Together AI API Key",
)
@classmethod
def sample_run_config(cls) -> Dict[str, Any]:
return {
"url": "https://api.together.xyz/v1",
"api_key": "${env.TOGETHER_API_KEY}",
}

4
llama_stack/providers/remote/inference/together/together.py
View file

@ -38,7 +38,7 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
from .config import TogetherImplConfig
model_aliases = [
MODEL_ALIASES = [
build_model_alias(
"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
CoreModelId.llama3_1_8b_instruct.value,
@ -78,7 +78,7 @@ class TogetherInferenceAdapter(
ModelRegistryHelper, Inference, NeedsRequestProviderData
):
def __init__(self, config: TogetherImplConfig) -> None:
ModelRegistryHelper.__init__(self, model_aliases)
ModelRegistryHelper.__init__(self, MODEL_ALIASES)
self.config = config
self.formatter = ChatFormat(Tokenizer.get_instance())