phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

model -> model_id for TGI

Browse source
This commit is contained in:
Ashwin Bharambe 2024-11-22 15:40:08 -08:00
parent c2c53d0272
commit 97dc5b68e5
2 changed files with 5 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/providers/remote/inference/tgi/tgi.py
View file

@ -74,7 +74,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
async def completion(
self,
model: str,
model_id: str,
content: InterleavedTextMedia,
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
@ -82,7 +82,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
request = CompletionRequest(
model=model,
model=model_id,
content=content,
sampling_params=sampling_params,
response_format=response_format,
@ -176,7 +176,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
async def chat_completion(
self,
model: str,
model_id: str,
messages: List[Message],
sampling_params: Optional[SamplingParams] = SamplingParams(),
tools: Optional[List[ToolDefinition]] = None,
@ -187,7 +187,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
request = ChatCompletionRequest(
model=model,
model=model_id,
messages=messages,
sampling_params=sampling_params,
tools=tools or [],
@ -256,7 +256,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
async def embeddings(
self,
model: str,
model_id: str,
contents: List[InterleavedTextMedia],
) -> EmbeddingsResponse:
raise NotImplementedError()