phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-02 19:34:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

jobs eval scoring

Browse source
This commit is contained in:
Xi Yan 2025-03-13 11:47:42 -07:00
parent 36320728bf
commit 775e8514b7
4 changed files with 92 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

36
docs/_static/llama-stack-spec.yaml vendored
View file

@ -142,7 +142,7 @@ paths:
schema:
$ref: '#/components/schemas/BatchCompletionRequest'
required: true
/v1/eval/job/{job_id}/cancel:
/v1/eval/jobs/{job_id}/cancel:
post:
responses:
'200':
@ -173,7 +173,7 @@ paths:
required: true
schema:
type: string
/v1/scoring/job/{job_id}/cancel:
/v1/scoring/jobs/{job_id}/cancel:
post:
responses:
'200':
@ -622,7 +622,7 @@ paths:
required: true
schema:
type: string
/v1/eval/job/{job_id}:
/v1/eval/jobs/{job_id}:
get:
responses:
'200':
@ -756,7 +756,7 @@ paths:
required: true
schema:
type: string
/v1/scoring/job/{job_id}:
/v1/scoring/jobs/{job_id}:
get:
responses:
'200':
@ -3514,20 +3514,30 @@ components:
If status of the job is failed, this will contain the error message.
type:
type: string
const: eval
default: eval
enum:
- batch_inference
- scoring
- evaluation
- post_training
default: evaluation
description: The type of the job.
result_files:
type: array
items:
type: string
description: The file ids of the eval results.
result_datasets:
type: array
items:
type: string
description: >-
The ids of the datasets containing the eval results.
benchmark_id:
type: string
description: The id of the benchmark to evaluate on.
candidate:
$ref: '#/components/schemas/EvalCandidate'
description: The candidate to evaluate on.
additionalProperties: false
required:
- id
@ -3539,6 +3549,7 @@ components:
- benchmark_id
- candidate
title: EvalJob
description: An evaluation job.
ModelCandidate:
type: object
properties:
@ -3693,22 +3704,32 @@ components:
If status of the job is failed, this will contain the error message.
type:
type: string
const: scoring
enum:
- batch_inference
- scoring
- evaluation
- post_training
default: scoring
description: The type of the job.
result_files:
type: array
items:
type: string
description: The file ids of the scoring results.
result_datasets:
type: array
items:
type: string
description: >-
The ids of the datasets containing the scoring results.
dataset_id:
type: string
description: The id of the dataset used for scoring.
scoring_fn_ids:
type: array
items:
type: string
description: The ids of the scoring functions used.
additionalProperties: false
required:
- id
@ -3720,6 +3741,7 @@ components:
- dataset_id
- scoring_fn_ids
title: ScoringJob
description: A scoring job.
CancelTrainingJobRequest:
type: object
properties: