experiment: llm_moe_hpc
kind: llm_moe
seed: 1
n_replicates: 1

# Scaled version of configs/llm/moe.yaml for an L40S (48 GB). At 7B the llm_merge fusion baseline
# (soup) already *composed* rather than diluted (merge 0.87 > best specialist 0.77, no dilution), so
# the sharp question here is whether the UNION operators (routing / max-merge) still add anything once
# the base is capable — i.e. does "merge, don't average" still bite at scale, or does a strong base
# make fusion and union converge? Either way is a reportable regime result.

base_model: Qwen/Qwen2.5-7B-Instruct
families: [lists, strings, arith]
n_train: 800          # only used if the cached specialists are absent (fresh on the HPC node)
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}