phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-10 04:08:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix

Browse source
This commit is contained in:
Xi Yan 2025-02-12 21:16:47 -08:00
parent 2d0f6865ac
commit 1395de57a6
3 changed files with 11 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

4
docs/_static/llama-stack-spec.html vendored
View file

@ -81,7 +81,7 @@
"deprecated": true
}
},
"/v1/eval-tasks/{benchmark_id}": {
"/v1/eval-tasks/{task_id}": {
"get": {
"responses": {
"200": {
@ -109,7 +109,7 @@
"parameters": [
{
"name": "task_id",
"in": "query",
"in": "path",
"required": true,
"schema": {
"type": "string"

4
docs/_static/llama-stack-spec.yaml vendored
View file

@ -35,7 +35,7 @@ paths:
$ref: '#/components/schemas/DeprecatedEvaluateRowsRequest'
required: true
deprecated: true
/v1/eval-tasks/{benchmark_id}:
/v1/eval-tasks/{task_id}:
get:
responses:
'200':
@ -51,7 +51,7 @@ paths:
description: ''
parameters:
- name: task_id
in: query
in: path
required: true
schema:
type: string

14
docs/notebooks/Llama_Stack_Benchmark_Evals.ipynb
View file

@ -1017,14 +1017,14 @@
" \"content\": SYSTEM_PROMPT_TEMPLATE.format(subject=subset),\n",
"}\n",
"\n",
"client.benchmarks.register(\n",
" benchmark_id=\"meta-reference::mmmu\",\n",
"client.eval_tasks.register(\n",
" eval_task_id=\"meta-reference::mmmu\",\n",
" dataset_id=f\"mmmu-{subset}-{split}\",\n",
" scoring_functions=[\"basic::regex_parser_multiple_choice_answer\"],\n",
")\n",
"\n",
"response = client.eval.evaluate_rows(\n",
" benchmark_id=\"meta-reference::mmmu\",\n",
" task_id=\"meta-reference::mmmu\",\n",
" input_rows=eval_rows,\n",
" scoring_functions=[\"basic::regex_parser_multiple_choice_answer\"],\n",
" task_config={\n",
@ -1196,8 +1196,8 @@
" provider_id=\"together\",\n",
")\n",
"\n",
"client.benchmarks.register(\n",
" benchmark_id=\"meta-reference::simpleqa\",\n",
"client.eval_tasks.register(\n",
" eval_task_id=\"meta-reference::simpleqa\",\n",
" dataset_id=simpleqa_dataset_id,\n",
" scoring_functions=[\"llm-as-judge::405b-simpleqa\"],\n",
")\n",
@ -1214,7 +1214,7 @@
" \"sampling_params\": {\n",
" \"strategy\": {\n",
" \"type\": \"greedy\",\n",
" },b\n",
" },\n",
" \"max_tokens\": 4096,\n",
" \"repeat_penalty\": 1.0,\n",
" },\n",
@ -1352,7 +1352,7 @@
"}\n",
"\n",
"response = client.eval.evaluate_rows(\n",
" benchmark_id=\"meta-reference::simpleqa\",\n",
" task_id=\"meta-reference::simpleqa\",\n",
" input_rows=eval_rows.rows,\n",
" scoring_functions=[\"llm-as-judge::405b-simpleqa\"],\n",
" task_config={\n",