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

# (Layer 2 / LLM prototype — blueprint C2/C4, the real-LLM image of E8): recombine specialist LLMs.
# Train one LoRA specialist per DISJOINT task family on a small open-weight base, then compare the
# base, each specialist, and their weight-space MERGES (soup = averaged deltas; ties = sign-reconciled
# union) on a held-out mixed test set. Tasks are procedurally generated and exactly verified (the
# "reality that says no"), and deliberately hard so specialists are decorrelated. Expect (per E8): the
# recombined model beats any single specialist overall AND is competent across ALL families
# (worst-family accuracy), which no single parent is. Falsifier: a single specialist matches the merge.

base_model: Qwen/Qwen2.5-0.5B-Instruct   # Apache-2.0; ~1 GB, fits 16 GB with room to spare
families: [lists, strings, arith]
n_train: 700
n_test: 100
epochs: 3
lora: {r: 16, alpha: 32}
merges: [soup, ties]

output: {dir: results/llm_merge}