phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-29 07:14:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Cleanup

Browse source
This commit is contained in:
Ashwin Bharambe 2024-09-30 17:28:55 -07:00
parent 1702aa5e3f
commit 6d8f59e359
3 changed files with 6 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/adapters/inference/bedrock/bedrock.py
View file

@ -18,7 +18,7 @@ from llama_stack.providers.utils.inference.routable import RoutableProviderForMo
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.providers.adapters.inference.bedrock.config import BedrockConfig
# mapping of Model SKUs to ollama models
BEDROCK_SUPPORTED_MODELS = {
"Llama3.1-8B-Instruct": "meta.llama3-1-8b-instruct-v1:0",
"Llama3.1-70B-Instruct": "meta.llama3-1-70b-instruct-v1:0",

1
llama_stack/providers/adapters/inference/fireworks/fireworks.py
View file

@ -22,6 +22,7 @@ from llama_stack.providers.utils.inference.augment_messages import (
from .config import FireworksImplConfig
FIREWORKS_SUPPORTED_MODELS = {
"Llama3.1-8B-Instruct": "fireworks/llama-v3p1-8b-instruct",
"Llama3.1-70B-Instruct": "fireworks/llama-v3p1-70b-instruct",

14
llama_stack/providers/adapters/inference/together/together.py
View file

@ -22,6 +22,7 @@ from llama_stack.providers.utils.inference.routable import RoutableProviderForMo
from .config import TogetherImplConfig
TOGETHER_SUPPORTED_MODELS = {
"Llama3.1-8B-Instruct": "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
"Llama3.1-70B-Instruct": "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
@ -167,17 +168,10 @@ class TogetherInferenceAdapter(
stream=True,
**options,
):
if chunk.choices[0].finish_reason:
if (
stop_reason is None and chunk.choices[0].finish_reason == "stop"
) or (
stop_reason is None and chunk.choices[0].finish_reason == "eos"
):
if finish_reason := chunk.choices[0].finish_reason:
if stop_reason is None and finish_reason in ["stop", "eos"]:
stop_reason = StopReason.end_of_turn
elif (
stop_reason is None
and chunk.choices[0].finish_reason == "length"
):
elif stop_reason is None and finish_reason == "length":
stop_reason = StopReason.out_of_tokens
break