mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-08-03 01:03:59 +00:00
pre-commit updates
This commit is contained in:
parent
7f1e4bf075
commit
a9e4d1f00e
1 changed files with 2 additions and 3 deletions
|
@ -29,12 +29,12 @@ from llama_stack.apis.inference import (
|
||||||
ToolPromptFormat,
|
ToolPromptFormat,
|
||||||
)
|
)
|
||||||
from llama_stack.apis.inference.inference import (
|
from llama_stack.apis.inference.inference import (
|
||||||
|
GreedySamplingStrategy,
|
||||||
OpenAIChatCompletion,
|
OpenAIChatCompletion,
|
||||||
OpenAIChatCompletionChunk,
|
OpenAIChatCompletionChunk,
|
||||||
OpenAICompletion,
|
OpenAICompletion,
|
||||||
OpenAIMessageParam,
|
OpenAIMessageParam,
|
||||||
OpenAIResponseFormatParam,
|
OpenAIResponseFormatParam,
|
||||||
GreedySamplingStrategy,
|
|
||||||
TopKSamplingStrategy,
|
TopKSamplingStrategy,
|
||||||
TopPSamplingStrategy,
|
TopPSamplingStrategy,
|
||||||
)
|
)
|
||||||
|
@ -242,8 +242,7 @@ class WatsonXInferenceAdapter(Inference, ModelRegistryHelper):
|
||||||
if isinstance(request.sampling_params.strategy, GreedySamplingStrategy):
|
if isinstance(request.sampling_params.strategy, GreedySamplingStrategy):
|
||||||
input_dict["params"][GenParams.TEMPERATURE] = 0.0
|
input_dict["params"][GenParams.TEMPERATURE] = 0.0
|
||||||
|
|
||||||
|
input_dict["params"][GenParams.STOP_SEQUENCES] = ["<|endoftext|>"]
|
||||||
input_dict["params"][GenParams.STOP_SEQUENCES] = ["<|endoftext|>"]
|
|
||||||
|
|
||||||
params = {
|
params = {
|
||||||
**input_dict,
|
**input_dict,
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue