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

fix spec

Browse source 
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
This commit is contained in:
Yuan Tang 2025-03-21 11:30:57 -04:00
parent 98274574f0
commit 9032544b2e
No known key found for this signature in database
2 changed files with 23 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

15
docs/_static/llama-stack-spec.html vendored
View file

@ -4053,28 +4053,33 @@
"type": "object",
"properties": {
"strategy": {
"$ref": "#/components/schemas/SamplingStrategy"
"$ref": "#/components/schemas/SamplingStrategy",
"description": "The sampling strategy."
},
"max_tokens": {
"type": "integer",
"default": 0
"default": 0,
"description": "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."
},
"repetition_penalty": {
"type": "number",
"default": 1.0
"default": 1.0,
"description": "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."
},
"stop": {
"type": "array",
"items": {
"type": "string"
}
},
"description": "Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence."
}
},
"additionalProperties": false,
"required": [
"strategy"
],
"title": "SamplingParams"
"title": "SamplingParams",
"description": "Sampling parameters."
},
"SamplingStrategy": {
"oneOf": [

13
docs/_static/llama-stack-spec.yaml vendored
View file

@ -2787,20 +2787,33 @@ components:
properties:
strategy:
$ref: '#/components/schemas/SamplingStrategy'
description: The sampling strategy.
max_tokens:
type: integer
default: 0
description: >-
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.
repetition_penalty:
type: number
default: 1.0
description: >-
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.
stop:
type: array
items:
type: string
description: >-
Up to 4 sequences where the API will stop generating further tokens. The
returned text will not contain the stop sequence.
additionalProperties: false
required:
- strategy
title: SamplingParams
description: Sampling parameters.
SamplingStrategy:
oneOf:
- $ref: '#/components/schemas/GreedySamplingStrategy'