phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 02:53:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Support for Llama3.2 models and Swift SDK (#98)

Browse source
This commit is contained in:
Ashwin Bharambe 2024-09-25 10:29:58 -07:00 • committed by GitHub
parent 95abbf576b
commit 56aed59eb4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
56 changed files with 3745 additions and 630 deletions
Download patch file Download diff file Expand all files Collapse all files

12
llama_stack/providers/adapters/inference/together/together.py
View file

@ -15,14 +15,16 @@ from llama_models.sku_list import resolve_model
from together import Together
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.providers.utils.inference.prepare_messages import prepare_messages
from llama_stack.providers.utils.inference.augment_messages import (
augment_messages_for_tools,
)
from .config import TogetherImplConfig
TOGETHER_SUPPORTED_MODELS = {
"Meta-Llama3.1-8B-Instruct": "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
"Meta-Llama3.1-70B-Instruct": "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
"Meta-Llama3.1-405B-Instruct": "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",
"Llama3.1-8B-Instruct": "meta-llama/Llama-3.1-8B-Instruct-Turbo",
"Llama3.1-70B-Instruct": "meta-llama/Llama-3.1-70B-Instruct-Turbo",
"Llama3.1-405B-Instruct": "meta-llama/Llama-3.1-405B-Instruct-Turbo",
}
@ -110,7 +112,7 @@ class TogetherInferenceAdapter(Inference):
# accumulate sampling params and other options to pass to together
options = self.get_together_chat_options(request)
together_model = self.resolve_together_model(request.model)
messages = prepare_messages(request)
messages = augment_messages_for_tools(request)
if not request.stream:
# TODO: might need to add back an async here