module Coppelius.Model

import Coppelius.Learner
import Model.Architecture
import Model.Config
import Model.Parameter
import Model.Word32
import Std.Word

-- Coppelius is the 60M-class dense attention transformer inspired by
-- huggingface.co/ajaxdavis/alpha-60m-base: 16 layers, width 512, 8 heads of
-- 64, FFN 1408, vocabulary 12288, context 1024, RoPE, RMSNorm, tied
-- embeddings, no matrix biases, and an exact-vocabulary objective.
--
-- The physically qualified SM86 realization recorded in docs/WORKLOG.md uses
-- LayerNorm and a gated GELU feed-forward block because those are the
-- maintained SM86 owners. The reference family remains explicit here rather
-- than silently encoding realization-specific padding or substitutions.
def modelCoppeliusVocab : StdU32 =
  12_288

def modelCoppeliusBlock : StdU32 =
  1_024

def modelCoppeliusLayers : StdU32 =
  16

def modelCoppeliusWidth : StdU32 =
  512

def modelCoppeliusHeads : StdU32 =
  8

def modelCoppeliusFfnWidth : StdU32 =
  1_408

def modelCoppeliusOne : StdU32 =
  1

-- the rotary positions' base: head-dimension pair i of a head width w turns
-- at theta_i = base^(-2i / w) radians per position
def coppeliusRotaryBase : Nat =
  10000

-- a fresh model's matrices (the embedding, and every layer's projections)
-- are drawn with standard deviation 1 / this; the norms' gains are one and
-- their shifts zero
def coppeliusInitializationDeviationDenominator : Nat =
  50

def modelCoppelius =
  (record
    ModelConfig
    (modelVocabSize = modelCoppeliusVocab)
    (modelBlockSize = modelCoppeliusBlock)
    (modelLayers = modelCoppeliusLayers)
    (modelWidth = modelCoppeliusWidth)
    (modelHeads = modelCoppeliusHeads)
    (modelFfnStoredWidth = modelCoppeliusFfnWidth)
    (modelExperts = modelCoppeliusOne)
    (modelTopK = modelCoppeliusOne)
    (modelRoute = (constructor ModelRouteKind ModelCyclicRoute))
    (modelStackedExperts = (constructor ModelBoolean ModelFalse))
    (modelHeadRank = (constructor ModelOptionalWord32 ModelNoWord32))
    (modelAttentionRank = (constructor ModelOptionalWord32 ModelNoWord32))
    (modelPositionEncoding = (constructor ModelPositionEncoding ModelRotaryPositions))
    (modelNormKind = (constructor ModelNormKind ModelRMSNormalization))
    (modelTieEmbeddings = (constructor ModelBoolean ModelTrue))
    (modelObjective = coppeliusObjective))