mirror of
https://github.com/open-jarvis/OpenJarvis.git
synced 2026-08-14 00:47:52 +00:00
95 lines
3.7 KiB
TOML
95 lines
3.7 KiB
TOML
# Archon cells. Inference-time architecture search (arXiv:2409.15254).
|
|
#
|
|
# Hybrid wiring: K local proposers (vLLM on 8001/8004) → 1 cloud ranker →
|
|
# 1 cloud fuser. method_cfg.architecture = "ensemble_rank_fuse" is the
|
|
# only non-debug preset; "single_local" exists for adapter smoke tests
|
|
# (no cloud calls).
|
|
#
|
|
# Naming: archon-<bench>-<local-short>-<cloud-short>-<arch>-<K>-<N>
|
|
|
|
# ---- Stage 1 smokes (n=3) ----
|
|
|
|
[cells.archon-gaia-qwen27b-opus-ensemble-K3-3]
|
|
method = "archon"
|
|
bench = "gaia"
|
|
n = 3
|
|
local = { model = "Qwen/Qwen3.5-27B-FP8", endpoint = "http://localhost:8001/v1" }
|
|
cloud = { model = "claude-opus-4-7", endpoint = "anthropic" }
|
|
method_cfg = { architecture = "ensemble_rank_fuse", n_samples = 3, max_tokens = 1024, temperature = 0.7 }
|
|
|
|
# Cheap sanity smoke: local-only generator, zero cloud spend. Use to verify
|
|
# vLLM + Archon plumbing without paying for Opus.
|
|
[cells.archon-gaia-qwen27b-singlelocal-3]
|
|
method = "archon"
|
|
bench = "gaia"
|
|
n = 3
|
|
local = { model = "Qwen/Qwen3.5-27B-FP8", endpoint = "http://localhost:8001/v1" }
|
|
cloud = { model = "claude-opus-4-7", endpoint = "anthropic" }
|
|
method_cfg = { architecture = "single_local", max_tokens = 8192 }
|
|
|
|
[cells.archon-swebenchverified-qwen27b-opus-ensemble-K3-3]
|
|
method = "archon"
|
|
bench = "swebench-verified"
|
|
n = 3
|
|
local = { model = "Qwen/Qwen3.5-27B-FP8", endpoint = "http://localhost:8001/v1" }
|
|
cloud = { model = "claude-opus-4-7", endpoint = "anthropic" }
|
|
method_cfg = { architecture = "ensemble_rank_fuse", n_samples = 3, max_tokens = 1024, temperature = 0.7 }
|
|
concurrency = 3
|
|
|
|
|
|
# ---- Stage 1.5 mid (n=30) ----
|
|
|
|
[cells.archon-gaia-qwen27b-opus-ensemble-K5-30]
|
|
method = "archon"
|
|
bench = "gaia"
|
|
n = 30
|
|
local = { model = "Qwen/Qwen3.5-27B-FP8", endpoint = "http://localhost:8001/v1" }
|
|
cloud = { model = "claude-opus-4-7", endpoint = "anthropic" }
|
|
method_cfg = { architecture = "ensemble_rank_fuse", n_samples = 5, max_tokens = 2048, temperature = 0.7 }
|
|
concurrency = 4
|
|
|
|
[cells.archon-gaia-qwen27b-singlelocal-30]
|
|
method = "archon"
|
|
bench = "gaia"
|
|
n = 30
|
|
local = { model = "Qwen/Qwen3.5-27B-FP8", endpoint = "http://localhost:8001/v1" }
|
|
cloud = { model = "claude-opus-4-7", endpoint = "anthropic" }
|
|
method_cfg = { architecture = "single_local", max_tokens = 8192 }
|
|
concurrency = 4
|
|
|
|
[cells.archon-gaia-gemma31b-opus-ensemble-K5-30]
|
|
method = "archon"
|
|
bench = "gaia"
|
|
n = 30
|
|
local = { model = "google/gemma-4-31B-it", endpoint = "http://localhost:8004/v1" }
|
|
cloud = { model = "claude-opus-4-7", endpoint = "anthropic" }
|
|
method_cfg = { architecture = "ensemble_rank_fuse", n_samples = 5, max_tokens = 2048, temperature = 0.7 }
|
|
|
|
[cells.archon-swebenchverified-qwen27b-opus-ensemble-K5-30]
|
|
method = "archon"
|
|
bench = "swebench-verified"
|
|
n = 30
|
|
local = { model = "Qwen/Qwen3.5-27B-FP8", endpoint = "http://localhost:8001/v1" }
|
|
cloud = { model = "claude-opus-4-7", endpoint = "anthropic" }
|
|
method_cfg = { architecture = "ensemble_rank_fuse", n_samples = 5, max_tokens = 2048, temperature = 0.7 }
|
|
concurrency = 3
|
|
|
|
|
|
# ---- Stage 2 full ----
|
|
|
|
[cells.archon-gaia-qwen27b-opus-ensemble-K5-165]
|
|
method = "archon"
|
|
bench = "gaia"
|
|
n = 165
|
|
local = { model = "Qwen/Qwen3.5-27B-FP8", endpoint = "http://localhost:8001/v1" }
|
|
cloud = { model = "claude-opus-4-7", endpoint = "anthropic" }
|
|
method_cfg = { architecture = "ensemble_rank_fuse", n_samples = 5, max_tokens = 2048, temperature = 0.7 }
|
|
|
|
[cells.archon-gaia-gemma31b-opus-ensemble-K5-165]
|
|
method = "archon"
|
|
bench = "gaia"
|
|
n = 165
|
|
local = { model = "google/gemma-4-31B-it", endpoint = "http://localhost:8004/v1" }
|
|
cloud = { model = "claude-opus-4-7", endpoint = "anthropic" }
|
|
method_cfg = { architecture = "ensemble_rank_fuse", n_samples = 5, max_tokens = 2048, temperature = 0.7 }
|