phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-13 04:22:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

full evals / full scoring flow

Browse source
This commit is contained in:
Xi Yan 2024-10-15 10:17:45 -07:00
parent cccd5be090
commit be4f395032
4 changed files with 88 additions and 109 deletions
Download patch file Download diff file Expand all files Collapse all files

74
docs/resources/llama-stack-spec.html
View file

@ -21,7 +21,7 @@
"info": {
"title": "[DRAFT] Llama Stack Specification",
"version": "0.0.1",
"description": "This is the specification of the llama stack that provides\n a set of endpoints and their corresponding interfaces that are tailored to\n best leverage Llama Models. The specification is still in draft and subject to change.\n Generated at 2024-10-15 00:44:26.278642"
"description": "This is the specification of the llama stack that provides\n a set of endpoints and their corresponding interfaces that are tailored to\n best leverage Llama Models. The specification is still in draft and subject to change.\n Generated at 2024-10-15 10:15:15.195382"
},
"servers": [
{
@ -5805,23 +5805,13 @@
"RunEvalTaskRequest": {
"type": "object",
"properties": {
"model": {
"type": "string"
},
"task": {
"type": "string"
},
"dataset": {
"type": "string"
},
"eval_task_config": {
"$ref": "#/components/schemas/EvaluateTaskConfig"
}
},
"additionalProperties": false,
"required": [
"model",
"task"
"eval_task_config"
]
},
"EvalResult": {
@ -6238,49 +6228,49 @@
],
"tags": [
{
"name": "Models"
},
{
"name": "BatchInference"
},
{
"name": "Inspect"
},
{
"name": "Evals"
},
{
"name": "Safety"
},
{
"name": "Shields"
},
{
"name": "Telemetry"
},
{
"name": "Agents"
},
{
"name": "Memory"
},
{
"name": "SyntheticDataGeneration"
"name": "Inference"
},
{
"name": "PostTraining"
},
{
"name": "Datasets"
"name": "Agents"
},
{
"name": "MemoryBanks"
},
{
"name": "Inspect"
},
{
"name": "Models"
},
{
"name": "Safety"
},
{
"name": "Evals"
},
{
"name": "BatchInference"
},
{
"name": "Shields"
},
{
"name": "SyntheticDataGeneration"
},
{
"name": "Telemetry"
},
{
"name": "RewardScoring"
},
{
"name": "Inference"
"name": "Datasets"
},
{
"name": "Memory"
},
{
"name": "BuiltinTool",