experiment: llm_merge_hpc
kind: llm_merge
seed: 1
n_replicates: 1

# Scaled version of configs/llm/merge.yaml for an L40S (48 GB): a bigger, more capable base so the
# specialists decorrelate cleanly and the "recombined model exceeds any single specialist" sign is
# less noisy than the 0.5B local prototype (where it was only marginal on overall accuracy).
# NOTE (code TODOs for the *definitive* run, not yet built): loop several seeds and report mean±CI;
# add more task families; and add a dilution-resistant / offspring-selected ("directed sex") merge.

base_model: Qwen/Qwen2.5-7B-Instruct    # ~15 GB bf16 + LoRA fits the L40S; fallback: 3B-Instruct
families: [lists, strings, arith]
n_train: 800
n_test: 200
epochs: 3
lora: {r: 16, alpha: 32}
merges: [soup, ties]

output: {dir: results/llm_merge_hpc}