# PRISME reference configuration: prisme_103m (see docs/architecture_spec.md)
model:
  name: transformer_enlarged_102m
  vocab_size: 32768
  d_model: 768
  n_layers: 12
  n_heads: 12
  n_kv_heads: 3
  ffn_width: 2144   # parameter-matched plain decoder: +2.65M params ~= PRISME workspace+controller (2.63M)
  max_seq_len: 4096
  rope_theta: 10000.0
  norm_eps: 1.0e-5
  tie_embeddings: true
  use_workspace: false
  w: 256
  ffn_w: 768
  n_slots: 16
  n_editor_blocks: 2
  n_editor_heads: 4
  r_max: 8
  eta_max: 0.25
  clip_c: 1.0
  readout_zero_init: true