phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-13 04:22:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

dell tgi adapter

Browse source
This commit is contained in:
Xi Yan 2024-10-16 16:35:46 -07:00
parent cfc97df6d5
commit cd1f1a86bf
5 changed files with 61 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

14
llama_stack/providers/adapters/inference/tgi/config.py
View file

@ -41,3 +41,17 @@ class InferenceAPIImplConfig(BaseModel):
default=None,
description="Your Hugging Face user access token (will default to locally saved token if not provided)",
)
@json_schema_type
class DellTGIImplConfig(BaseModel):
url: str = Field(
description="The URL for the Dell TGI endpoint (e.g. 'http://localhost:8080')",
)
hf_model_name: str = Field(
description="The model ID of the model on the Hugging Face Hub (e.g. 'meta-llama/Meta-Llama-3.1-70B-Instruct')",
)
api_token: Optional[str] = Field(
default=None,
description="A bearer token if your TGI endpoint is protected.",
)