mirror of
https://github.com/agentscope-ai/ReMe.git
synced 2026-09-14 23:21:04 +00:00
9975bb37b9
Some checks failed
CI / Python tests / Unit Tests - py3.12 (push) Waiting to run
CI / Python tests / Unit Tests - py3.13 (push) Waiting to run
CI / Windows / CLI smoke - py3.11 (push) Waiting to run
Deploy / Documentation / Build documentation (push) Waiting to run
Deploy / Documentation / deploy (push) Blocked by required conditions
CI / Python packages / Build and verify distributions (push) Waiting to run
CI / Python quality / Pre-commit (push) Waiting to run
CI / Python tests / Unit Tests - py3.11 (push) Waiting to run
Security / CodeQL / Analyze javascript-typescript (push) Waiting to run
Security / CodeQL / Analyze python (push) Waiting to run
CI / Documentation / Test and build documentation (push) Has been cancelled
25 lines
1.1 KiB
YAML
25 lines
1.1 KiB
YAML
# BEAM evaluation configuration
|
|
# This file controls what/how to evaluate.
|
|
|
|
dataset:
|
|
beam_root: "benchmark/beam/dataset/BEAM" # BEAM dataset root
|
|
chat_size: "1M" # 100K | 500K | 1M | 10M (dataset variant)
|
|
case_ids: [] # empty = all cases; or ["1", "2", "3"]
|
|
start_index: 0 # first case index (for pagination)
|
|
num_items: 0 # 0 = all cases; >0 = limit
|
|
workspace_root: "benchmark/beam/workspaces/beam" # workspace root for case workspaces
|
|
|
|
evaluation:
|
|
num_workers: 20 # 0 = auto; 1 = sequential; >1 = parallel (per-case)
|
|
compress_session: false # true = compress session chunks in search_v2 (query-aware); false = no compression
|
|
|
|
reme:
|
|
config: "benchmark" # shared ReMe benchmark preset
|
|
plugins: [beam, beam-judge]
|
|
|
|
output:
|
|
dir: "benchmark/beam/results"
|
|
log_dir: "logs" # log directory (relative to project root)
|
|
log_prefix: "beam" # benchmark name used in log filenames
|
|
log_to_console: true
|
|
log_to_file: true
|