Giorgio Gilestro
8da0dac007
Adds the union-preserving recombination operator that llm_merge lacked (E8's max,
not mean): keep each specialist LoRA intact and SELECT the right one per prompt
(MoE router: oracle, or training-free nearest-centroid over base embeddings) or
per module (max_merge = winner-take-all by delta norm). src/llm/moe.py, kind
llm_moe, reuses the cached specialists.
Result — a clean regime boundary for "merge, don't average":
- 0.5B: union wins. Routing 0.74 / worst-family 0.43 > soup 0.64 / 0.26, with no
dilution (recovers each specialist's own-family peak). E8's max > mean in real
weights, because at a weak base averaging dilutes.
- 7B (Imperial CX3, L40S, 9 min): the ordering INVERTS. Fusion wins — soup 0.87 >
routing 0.84 > max_merge 0.78. Routing is capped at the best parent per family;
fusion blends and, given a capable base, COMPOSES beyond any parent (soup lists
0.62 > spec 0.57). Selection can't synthesise better than its best component;
averaging-that-composes can.
So "merge, don't average" (E4/E8) is a weak-parent / small-model law, not
universal: union wins under dilution, fusion wins under composition. Refines E8
(its additive-landscape max>mean assumed no compositional headroom). The operator
to want is fusion-that-composes + offspring selection = the directed-sex ideal
(E10) — the natural next experiment.
Honest riders: the learned router is trivially perfect (lexically-distinct
families), and router-free max_merge is the weakest union (not input-adaptive).
+2 router unit tests (127 green). Results in results/llm_moe{,_hpc}/ (parquet
gitignored per the reproducibility contract).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
28 lines
418 B
YAML
28 lines
418 B
YAML
experiment: llm_moe_hpc
|
|
seed: 1
|
|
n_replicates: 1
|
|
source_config:
|
|
experiment: llm_moe_hpc
|
|
kind: llm_moe
|
|
seed: 1
|
|
n_replicates: 1
|
|
base_model: Qwen/Qwen2.5-7B-Instruct
|
|
families:
|
|
- lists
|
|
- strings
|
|
- arith
|
|
n_train: 800
|
|
n_test: 200
|
|
n_route: 48
|
|
epochs: 3
|
|
lora:
|
|
r: 16
|
|
alpha: 32
|
|
operators:
|
|
- soup
|
|
- ties
|
|
- moe_oracle
|
|
- moe_learned
|
|
- max_merge
|
|
output:
|
|
dir: results/llm_moe_hpc
|