Merge-related changes.

This commit is contained in:
ilya-kolchinsky 2025-04-02 19:56:44 +02:00
commit 60e9f46856
456 changed files with 38636 additions and 10892 deletions

View file

@ -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:
@ -54,7 +54,8 @@ providers:
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
config:
excluded_categories: []
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
@ -62,25 +63,37 @@ 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: ${env.OTEL_SERVICE_NAME:llama-stack}
service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
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
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/open-benchmark}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/open-benchmark}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config: {}
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/open-benchmark}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic
@ -114,18 +127,13 @@ 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 +149,94 @@ 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
- purpose: eval/messages-answer
source:
type: uri
uri: huggingface://datasets/llamastack/simpleqa?split=train
metadata: {}
dataset_id: simpleqa
- purpose: eval/messages-answer
source:
type: uri
uri: huggingface://datasets/llamastack/mmlu_cot?split=test&name=all
metadata: {}
dataset_id: mmlu_cot
- purpose: eval/messages-answer
source:
type: uri
uri: huggingface://datasets/llamastack/gpqa_0shot_cot?split=test&name=gpqa_main
metadata: {}
dataset_id: gpqa_cot
- purpose: eval/messages-answer
source:
type: uri
uri: huggingface://datasets/llamastack/math_500?split=test
metadata: {}
dataset_id: math_500
- purpose: eval/messages-answer
source:
type: uri
uri: huggingface://datasets/llamastack/bfcl_v3?split=train
metadata: {}
dataset_id: bfcl
- purpose: eval/messages-answer
source:
type: uri
uri: huggingface://datasets/llamastack/IfEval?split=train
metadata: {}
dataset_id: ifeval
- purpose: eval/messages-answer
source:
type: uri
uri: huggingface://datasets/llamastack/docvqa?split=val
metadata: {}
dataset_id: docvqa
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
- dataset_id: bfcl
scoring_functions:
- basic::bfcl
metadata: {}
benchmark_id: meta-reference-bfcl
- dataset_id: ifeval
scoring_functions:
- basic::ifeval
metadata: {}
benchmark_id: meta-reference-ifeval
- dataset_id: docvqa
scoring_functions:
- basic::docvqa
metadata: {}
benchmark_id: meta-reference-docvqa
tool_groups:
- toolgroup_id: builtin::websearch
provider_id: tavily-search
@ -226,5 +244,6 @@ tool_groups:
provider_id: rag-runtime
- toolgroup_id: builtin::code_interpreter
provider_id: code-interpreter
preprocessors: []
server:
port: 8321