phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-08 19:10:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

slight upgrade to CLI

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-06 18:02:47 -07:00 • committed by Ashwin Bharambe
parent 1550187cd8
commit 099a95b614
4 changed files with 23 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/adapters/inference/tgi/config.py
View file

@ -34,7 +34,7 @@ class InferenceEndpointImplConfig(BaseModel):
@json_schema_type
class InferenceAPIImplConfig(BaseModel):
model_id: str = Field(
huggingface_repo: 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(

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

@ -243,7 +243,7 @@ class TGIAdapter(_HfAdapter):
class InferenceAPIAdapter(_HfAdapter):
async def initialize(self, config: InferenceAPIImplConfig) -> None:
self.client = AsyncInferenceClient(
model=config.model_id, token=config.api_token
model=config.huggingface_repo, token=config.api_token
)
endpoint_info = await self.client.get_endpoint_info()
self.max_tokens = endpoint_info["max_total_tokens"]