forked from phoenix-oss/llama-stack-mirror
feat: Add open benchmark template codegen (#1579)
## What does this PR do? As title, add codegen for open-benchmark template ## test checked the new generated run.yaml file and it's identical before and after the change Also add small improvement to together template so that missing TOGETHER_API_KEY won't crash the server which is the consistent user experience as other remote providers
This commit is contained in:
Botao Chen
GitHub
parent
4eee349acd
commit
0b0be70605
8 changed files with 430 additions and 84 deletions
|
|
@ -38,7 +38,7 @@ providers:
|
|||
- provider_id: sqlite-vec
|
||||
provider_type: inline::sqlite-vec
|
||||
config:
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dev}/sqlite_vec.db
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/open-benchmark}/sqlite_vec.db
|
||||
- provider_id: ${env.ENABLE_CHROMADB+chromadb}
|
||||
provider_type: remote::chromadb
|
||||
config:
|
||||
|
|
@ -62,14 +62,14 @@ providers:
|
|||
persistence_store:
|
||||
type: sqlite
|
||||
namespace: null
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dev}/agents_store.db
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/open-benchmark}/agents_store.db
|
||||
telemetry:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
|
||||
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/dev/trace_store.db}
|
||||
sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/open-benchmark/trace_store.db}
|
||||
eval:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
|
|
@ -114,18 +114,13 @@ providers:
|
|||
config: {}
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/dev}/registry.db
|
||||
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/open-benchmark}/registry.db
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: openai/gpt-4o
|
||||
provider_id: openai
|
||||
provider_model_id: openai/gpt-4o
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-3.1-405B-Instruct
|
||||
provider_id: together
|
||||
provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: anthropic/claude-3-5-sonnet-latest
|
||||
provider_id: anthropic
|
||||
|
|
@ -141,84 +136,95 @@ models:
|
|||
provider_id: groq
|
||||
provider_model_id: groq/llama-3.3-70b-versatile
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-3.1-405B-Instruct
|
||||
provider_id: together
|
||||
provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
|
||||
model_type: llm
|
||||
shields:
|
||||
- shield_id: meta-llama/Llama-Guard-3-8B
|
||||
vector_dbs: []
|
||||
datasets:
|
||||
- dataset_id: simpleqa
|
||||
provider_id: huggingface
|
||||
url:
|
||||
uri: https://huggingface.co/datasets/llamastack/simpleqa
|
||||
metadata:
|
||||
path: llamastack/simpleqa
|
||||
name:
|
||||
split: train
|
||||
dataset_schema:
|
||||
input_query:
|
||||
type: string
|
||||
expected_answer:
|
||||
type: string
|
||||
chat_completion_input:
|
||||
type: string
|
||||
- dataset_id: mmlu_cot
|
||||
provider_id: huggingface
|
||||
url:
|
||||
uri: https://huggingface.co/datasets/llamastack/mmlu_cot
|
||||
metadata:
|
||||
path: llamastack/mmlu_cot
|
||||
name: all
|
||||
split: test
|
||||
dataset_schema:
|
||||
input_query:
|
||||
type: string
|
||||
expected_answer:
|
||||
type: string
|
||||
chat_completion_input:
|
||||
type: string
|
||||
- dataset_id: gpqa_cot
|
||||
provider_id: huggingface
|
||||
url:
|
||||
uri: https://huggingface.co/datasets/llamastack/gpqa_0shot_cot
|
||||
metadata:
|
||||
path: llamastack/gpqa_0shot_cot
|
||||
name: gpqa_main
|
||||
split: train
|
||||
dataset_schema:
|
||||
input_query:
|
||||
type: string
|
||||
expected_answer:
|
||||
type: string
|
||||
chat_completion_input:
|
||||
type: string
|
||||
- dataset_id: math_500
|
||||
provider_id: huggingface
|
||||
url:
|
||||
uri: https://huggingface.co/datasets/llamastack/math_500
|
||||
metadata:
|
||||
path: llamastack/math_500
|
||||
name:
|
||||
split: test
|
||||
dataset_schema:
|
||||
input_query:
|
||||
type: string
|
||||
expected_answer:
|
||||
type: string
|
||||
chat_completion_input:
|
||||
type: string
|
||||
- dataset_schema:
|
||||
input_query:
|
||||
type: string
|
||||
expected_answer:
|
||||
type: string
|
||||
chat_completion_input:
|
||||
type: string
|
||||
url:
|
||||
uri: https://huggingface.co/datasets/llamastack/simpleqa
|
||||
metadata:
|
||||
path: llamastack/simpleqa
|
||||
split: train
|
||||
dataset_id: simpleqa
|
||||
provider_id: huggingface
|
||||
- dataset_schema:
|
||||
input_query:
|
||||
type: string
|
||||
expected_answer:
|
||||
type: string
|
||||
chat_completion_input:
|
||||
type: string
|
||||
url:
|
||||
uri: https://huggingface.co/datasets/llamastack/mmlu_cot
|
||||
metadata:
|
||||
path: llamastack/mmlu_cot
|
||||
name: all
|
||||
split: test
|
||||
dataset_id: mmlu_cot
|
||||
provider_id: huggingface
|
||||
- dataset_schema:
|
||||
input_query:
|
||||
type: string
|
||||
expected_answer:
|
||||
type: string
|
||||
chat_completion_input:
|
||||
type: string
|
||||
url:
|
||||
uri: https://huggingface.co/datasets/llamastack/gpqa_0shot_cot
|
||||
metadata:
|
||||
path: llamastack/gpqa_0shot_cot
|
||||
name: gpqa_main
|
||||
split: train
|
||||
dataset_id: gpqa_cot
|
||||
provider_id: huggingface
|
||||
- dataset_schema:
|
||||
input_query:
|
||||
type: string
|
||||
expected_answer:
|
||||
type: string
|
||||
chat_completion_input:
|
||||
type: string
|
||||
url:
|
||||
uri: https://huggingface.co/datasets/llamastack/math_500
|
||||
metadata:
|
||||
path: llamastack/math_500
|
||||
split: test
|
||||
dataset_id: math_500
|
||||
provider_id: huggingface
|
||||
scoring_fns: []
|
||||
benchmarks:
|
||||
- benchmark_id: meta-reference-simpleqa
|
||||
dataset_id: simpleqa
|
||||
scoring_functions: ["llm-as-judge::405b-simpleqa"]
|
||||
- benchmark_id: meta-reference-mmlu-cot
|
||||
dataset_id: mmlu_cot
|
||||
scoring_functions: ["basic::regex_parser_multiple_choice_answer"]
|
||||
- benchmark_id: meta-reference-gpqa-cot
|
||||
dataset_id: gpqa_cot
|
||||
scoring_functions: ["basic::regex_parser_multiple_choice_answer"]
|
||||
- benchmark_id: meta-reference-math-500
|
||||
dataset_id: math_500
|
||||
scoring_functions: ["basic::regex_parser_math_response"]
|
||||
- dataset_id: simpleqa
|
||||
scoring_functions:
|
||||
- llm-as-judge::405b-simpleqa
|
||||
metadata: {}
|
||||
benchmark_id: meta-reference-simpleqa
|
||||
- dataset_id: mmlu_cot
|
||||
scoring_functions:
|
||||
- basic::regex_parser_multiple_choice_answer
|
||||
metadata: {}
|
||||
benchmark_id: meta-reference-mmlu-cot
|
||||
- dataset_id: gpqa_cot
|
||||
scoring_functions:
|
||||
- basic::regex_parser_multiple_choice_answer
|
||||
metadata: {}
|
||||
benchmark_id: meta-reference-gpqa-cot
|
||||
- dataset_id: math_500
|
||||
scoring_functions:
|
||||
- basic::regex_parser_math_response
|
||||
metadata: {}
|
||||
benchmark_id: meta-reference-math-500
|
||||
tool_groups:
|
||||
- toolgroup_id: builtin::websearch
|
||||
provider_id: tavily-search
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue