phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-06 02:32:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add docs

Browse source 
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
This commit is contained in:
Yuan Tang 2025-03-21 11:23:27 -04:00
parent e91098d86e
commit 7968148bca
No known key found for this signature in database
1 changed files with 10 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/models/llama/datatypes.py
View file

@ -197,6 +197,16 @@ SamplingStrategy = register_schema(
@json_schema_type
class SamplingParams(BaseModel):
"""Sampling parameters.
:param strategy: The sampling strategy.
:param max_tokens: The maximum number of tokens that can be generated in the completion. The token count of
your prompt plus max_tokens cannot exceed the model's context length.
:param repetition_penalty: Number between -2.0 and 2.0. Positive values penalize new tokens
based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
:param stop: Up to 4 sequences where the API will stop generating further tokens.
The returned text will not contain the stop sequence.
"""
strategy: SamplingStrategy = Field(default_factory=GreedySamplingStrategy)
max_tokens: Optional[int] = 0