experiment: llm_moe
seed: 1
n_replicates: 1
source_config:
  experiment: llm_moe
  kind: llm_moe
  seed: 1
  n_replicates: 1
  base_model: Qwen/Qwen2.5-0.5B-Instruct
  families:
  - lists
  - strings
  - arith
  n_train: 700
  n_test: 100
  n_route: 32
  epochs: 3
  lora:
    r: 16
    alpha: 32
  operators:
  - soup
  - ties
  - moe_oracle
  - moe_learned
  - max_merge
  output:
    dir: results/llm_moe