phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-17 15:13:49 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Safety tests work

Browse source
This commit is contained in:
Ashwin Bharambe 2024-11-04 12:27:05 -08:00 • committed by Ashwin Bharambe
parent 66b658dcce
commit 2ed0267fbb
3 changed files with 100 additions and 88 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -38,13 +38,14 @@ TOGETHER_SUPPORTED_MODELS = {
"Llama3.2-3B-Instruct": "meta-llama/Llama-3.2-3B-Instruct-Turbo",
"Llama3.2-11B-Vision-Instruct": "meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo",
"Llama3.2-90B-Vision-Instruct": "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo",
"Llama-Guard-3-8B": "meta-llama/Meta-Llama-Guard-3-8B",
"Llama-Guard-3-11B-Vision": "meta-llama/Llama-Guard-3-11B-Vision-Turbo",
}
class TogetherInferenceAdapter(
ModelRegistryHelper, Inference, NeedsRequestProviderData
):
def __init__(self, config: TogetherImplConfig) -> None:
ModelRegistryHelper.__init__(
self, stack_to_provider_models_map=TOGETHER_SUPPORTED_MODELS
@ -150,7 +151,6 @@ class TogetherInferenceAdapter(
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
request = ChatCompletionRequest(
model=model,
messages=messages,