Upload aether_pkg/modeling_aether_v2_7way.py.pre_moe with huggingface_hub

aether_pkg/modeling_aether_v2_7way.py.pre_moe

@@ -0,0 +1,826 @@
+# coding=utf-8
+# Copyright 2026 VIDRAFT (비드래프트). All rights reserved.
+#
+# AETHER-V2-7way: 7-aware attention + 7×7 Latin Square 49-layer MoE
+# Built upon HuggingFace Transformers conventions.
+#
+# Architecture:
+#   - 49 layers organized as 7×7 Latin Square
+#   - 7 distinct attention types (NSA, Differential, Full, Linear, Sliding, Compress, Hybrid)
+#   - 25 experts per layer, top-7 active per token
+#   - Each row of latin square = 1 cycle of 7 attention types
+#   - Each column = different ordering (Latin square property)
+#
+# Layer index → (row, col) → attention type via LATIN_SQUARE_7x7
+#
+"""PyTorch AETHER-V2-7way model."""
+
+from __future__ import annotations
+import math
+import warnings
+from typing import List, Optional, Tuple, Union
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from torch.nn import CrossEntropyLoss
+
+from transformers.activations import ACT2FN
+from transformers.cache_utils import Cache, DynamicCache
+from transformers.modeling_outputs import (
+    BaseModelOutputWithPast,
+    CausalLMOutputWithPast,
+    MoeCausalLMOutputWithPast,
+    MoeModelOutputWithPast,
+)
+from transformers.modeling_utils import PreTrainedModel
+from transformers.utils import logging
+
+from .configuration_aether_v2_7way import AETHERV27wayConfig
+
+# 7-aware attention modules (already authored, in v2_attentions/)
+from .v2_attentions.nsa import NSAAttention
+from .v2_attentions.differential import DifferentialAttention
+
+logger = logging.get_logger(__name__)
+
+
+# =============================================================================
+# 7×7 Latin Square — Layer → (attention_type, ffn_phase) 매핑
+# =============================================================================
+# Latin Square property: each row & column has each of {0..6} exactly once.
+# row = layer // 7   (0..6)
+# col = layer % 7    (0..6)
+# attention_type = LATIN_SQUARE_7x7[row][col]
+#
+# 5-element cyclic FFN phase (오행 상생 — Q2B OhengGate inspired):
+# ffn_phase = layer % 5
+#
+LATIN_SQUARE_7x7 = [
+    [0, 1, 2, 3, 4, 5, 6],   # row 0: identity
+    [1, 2, 3, 4, 5, 6, 0],   # row 1: shift +1
+    [2, 3, 4, 5, 6, 0, 1],   # row 2: shift +2
+    [3, 4, 5, 6, 0, 1, 2],   # row 3: shift +3
+    [4, 5, 6, 0, 1, 2, 3],   # row 4: shift +4
+    [5, 6, 0, 1, 2, 3, 4],   # row 5: shift +5
+    [6, 0, 1, 2, 3, 4, 5],   # row 6: shift +6
+]
+
+# Attention type names (0..6)
+ATTN_TYPES = [
+    "nsa",            # 0: Native Sparse Attention (3-branch)
+    "differential",   # 1: Differential Attention (lambda-gated)
+    "full",           # 2: Full Attention (standard)
+    "linear",         # 3: Linear Attention (Mamba-style)
+    "sliding",        # 4: Sliding Window Attention
+    "compress",       # 5: Compress-only branch (NSA subset)
+    "hybrid",         # 6: NSA+Differential combined
+]
+
+
+def get_attention_type(layer_idx: int) -> str:
+    """Layer index → attention type via Latin Square."""
+    row = layer_idx // 7
+    col = layer_idx % 7
+    type_idx = LATIN_SQUARE_7x7[row][col]
+    return ATTN_TYPES[type_idx]
+
+
+def get_ffn_phase(layer_idx: int) -> int:
+    """Layer index → 5-element cyclic phase (오행)."""
+    return layer_idx % 5
+
+
+# =============================================================================
+# Rotary Position Embedding (RoPE)
+# =============================================================================
+class AETHERV27wayRotaryEmbedding(nn.Module):
+    def __init__(self, dim: int, max_pos: int = 4096, base: float = 10000.0, device=None):
+        super().__init__()
+        self.dim = dim
+        self.max_pos = max_pos
+        self.base = base
+        inv_freq = 1.0 / (base ** (torch.arange(0, dim, 2, dtype=torch.float32) / dim))
+        self.register_buffer("inv_freq", inv_freq, persistent=False)
+        self._build_cos_sin_cache(max_pos, device or torch.device("cpu"))
+
+    def _build_cos_sin_cache(self, seq_len: int, device, dtype=torch.float32):
+        t = torch.arange(seq_len, device=device, dtype=torch.float32)
+        freqs = torch.outer(t, self.inv_freq)
+        emb = torch.cat([freqs, freqs], dim=-1)
+        self.register_buffer("cos_cached", emb.cos().to(dtype), persistent=False)
+        self.register_buffer("sin_cached", emb.sin().to(dtype), persistent=False)
+
+    @torch.no_grad()
+    def forward(self, x: torch.Tensor, position_ids: torch.Tensor):
+        if position_ids.max() >= self.cos_cached.size(0):
+            self._build_cos_sin_cache(int(position_ids.max() + 1), x.device, x.dtype)
+        cos = self.cos_cached[position_ids].to(x.dtype)
+        sin = self.sin_cached[position_ids].to(x.dtype)
+        return cos, sin
+
+
+def rotate_half(x: torch.Tensor) -> torch.Tensor:
+    x1, x2 = x.chunk(2, dim=-1)
+    return torch.cat([-x2, x1], dim=-1)
+
+
+def apply_rotary_pos_emb(q, k, cos, sin, unsqueeze_dim=1):
+    cos = cos.unsqueeze(unsqueeze_dim)
+    sin = sin.unsqueeze(unsqueeze_dim)
+    q_embed = (q * cos) + (rotate_half(q) * sin)
+    k_embed = (k * cos) + (rotate_half(k) * sin)
+    return q_embed, k_embed
+
+
+# =============================================================================
+# RMSNorm
+# =============================================================================
+class AETHERV27wayRMSNorm(nn.Module):
+    def __init__(self, hidden_size: int, eps: float = 1e-6):
+        super().__init__()
+        self.weight = nn.Parameter(torch.ones(hidden_size))
+        self.eps = eps
+
+    def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
+        in_dtype = hidden_states.dtype
+        hidden_states = hidden_states.to(torch.float32)
+        variance = hidden_states.pow(2).mean(-1, keepdim=True)
+        hidden_states = hidden_states * torch.rsqrt(variance + self.eps)
+        return self.weight * hidden_states.to(in_dtype)
+
+
+# =============================================================================
+# Standard Multi-Head Attention (Full Attention type)
+# =============================================================================
+class FullAttention(nn.Module):
+    """Standard multi-head attention with GQA support."""
+
+    def __init__(self, config: AETHERV27wayConfig, layer_idx: int):
+        super().__init__()
+        self.config = config
+        self.layer_idx = layer_idx
+        self.hidden_size = config.hidden_size
+        self.num_heads = config.num_attention_heads
+        self.num_kv_heads = getattr(config, "num_key_value_heads", config.num_attention_heads)
+        self.head_dim = config.head_dim
+        self.num_kv_groups = self.num_heads // self.num_kv_heads
+
+        self.q_proj = nn.Linear(self.hidden_size, self.num_heads * self.head_dim, bias=False)
+        self.k_proj = nn.Linear(self.hidden_size, self.num_kv_heads * self.head_dim, bias=False)
+        self.v_proj = nn.Linear(self.hidden_size, self.num_kv_heads * self.head_dim, bias=False)
+        self.o_proj = nn.Linear(self.num_heads * self.head_dim, self.hidden_size, bias=False)
+
+        self.rotary = AETHERV27wayRotaryEmbedding(
+            self.head_dim, config.max_position_embeddings, config.rope_theta,
+        )
+
+    def _repeat_kv(self, x: torch.Tensor) -> torch.Tensor:
+        if self.num_kv_groups == 1:
+            return x
+        bsz, n_kv, seq, dim = x.shape
+        return x[:, :, None, :, :].expand(bsz, n_kv, self.num_kv_groups, seq, dim).reshape(
+            bsz, n_kv * self.num_kv_groups, seq, dim,
+        )
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        attention_mask: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        past_key_value: Optional[Cache] = None,
+        use_cache: bool = False,
+        **kwargs,
+    ) -> Tuple[torch.Tensor, Optional[Cache]]:
+        bsz, q_len, _ = hidden_states.size()
+
+        q = self.q_proj(hidden_states).view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2)
+        k = self.k_proj(hidden_states).view(bsz, q_len, self.num_kv_heads, self.head_dim).transpose(1, 2)
+        v = self.v_proj(hidden_states).view(bsz, q_len, self.num_kv_heads, self.head_dim).transpose(1, 2)
+
+        cos, sin = self.rotary(v, position_ids)
+        q, k = apply_rotary_pos_emb(q, k, cos, sin)
+
+        if past_key_value is not None:
+            k, v = past_key_value.update(k, v, self.layer_idx)
+
+        k = self._repeat_kv(k)
+        v = self._repeat_kv(v)
+
+        attn_out = F.scaled_dot_product_attention(
+            q, k, v,
+            attn_mask=(attention_mask.to(q.dtype) if attention_mask is not None else None),
+            dropout_p=0.0 if not self.training else self.config.attention_dropout,
+            is_causal=(attention_mask is None and q_len > 1),
+        )
+        attn_out = attn_out.transpose(1, 2).contiguous().view(bsz, q_len, -1)
+        return self.o_proj(attn_out), past_key_value
+
+
+# =============================================================================
+# Linear Attention (Mamba-style, simplified)
+# =============================================================================
+class LinearAttention(nn.Module):
+    """Linear attention (Mamba/RWKV-inspired) for long-context efficiency."""
+
+    def __init__(self, config: AETHERV27wayConfig, layer_idx: int):
+        super().__init__()
+        self.config = config
+        self.layer_idx = layer_idx
+        self.hidden_size = config.hidden_size
+        self.num_heads = config.num_attention_heads
+        self.head_dim = config.head_dim
+        self.q_proj = nn.Linear(self.hidden_size, self.num_heads * self.head_dim, bias=False)
+        self.k_proj = nn.Linear(self.hidden_size, self.num_heads * self.head_dim, bias=False)
+        self.v_proj = nn.Linear(self.hidden_size, self.num_heads * self.head_dim, bias=False)
+        self.gate = nn.Linear(self.hidden_size, self.num_heads * self.head_dim, bias=False)
+        self.o_proj = nn.Linear(self.num_heads * self.head_dim, self.hidden_size, bias=False)
+        self.norm = AETHERV27wayRMSNorm(self.head_dim, eps=config.rms_norm_eps)
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        attention_mask: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        past_key_value: Optional[Cache] = None,
+        use_cache: bool = False,
+        **kwargs,
+    ) -> Tuple[torch.Tensor, Optional[Cache]]:
+        bsz, q_len, _ = hidden_states.size()
+        # FIX 5/8: causal mask 누락 fix — SDPA causal fallback (Linear의 효율 손실, but 안전)
+        q = self.q_proj(hidden_states).view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2)
+        k = self.k_proj(hidden_states).view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2)
+        v = self.v_proj(hidden_states).view(bsz, q_len, self.num_heads, self.head_dim).transpose(1, 2)
+        g = self.gate(hidden_states).view(bsz, q_len, self.num_heads, self.head_dim).sigmoid()
+
+        out = F.scaled_dot_product_attention(q, k, v, dropout_p=0.0, is_causal=True)
+        out = out.transpose(1, 2).contiguous()  # (bsz, q_len, num_heads, head_dim)
+        out = out * g
+        out = self.norm(out).reshape(bsz, q_len, -1)
+        return self.o_proj(out), past_key_value
+
+
+# =============================================================================
+# Sliding Window Attention
+# =============================================================================
+class SlidingWindowAttention(FullAttention):
+    """Standard MHA but limited to local window for efficiency."""
+
+    def __init__(self, config: AETHERV27wayConfig, layer_idx: int):
+        super().__init__(config, layer_idx)
+        self.window_size = getattr(config, "sliding_window_size", 512)
+
+    def forward(self, hidden_states, attention_mask=None, position_ids=None,
+                past_key_value=None, use_cache=False, **kwargs):
+        bsz, q_len, _ = hidden_states.size()
+        if attention_mask is None and q_len > self.window_size:
+            mask = torch.ones(q_len, q_len, dtype=torch.bool, device=hidden_states.device)
+            mask = torch.tril(mask) & torch.triu(mask, diagonal=-self.window_size)
+            attention_mask = torch.where(mask, 0.0, float("-inf")).unsqueeze(0).unsqueeze(0)
+        return super().forward(hidden_states, attention_mask, position_ids, past_key_value, use_cache, **kwargs)
+
+
+# =============================================================================
+# Compress Attention (NSA-subset, just compress branch)
+# =============================================================================
+class CompressAttention(nn.Module):
+    """Compress branch: reduce KV cache via local average, then full attention on compressed."""
+
+    def __init__(self, config: AETHERV27wayConfig, layer_idx: int):
+        super().__init__()
+        self.config = config
+        self.layer_idx = layer_idx
+        self.compress_block = getattr(config, "compress_block_size", 16)
+        self.full_attn = FullAttention(config, layer_idx)
+
+    def forward(self, hidden_states, attention_mask=None, position_ids=None,
+                past_key_value=None, use_cache=False, **kwargs):
+        # FIX 5/8: Block-mean broadcast가 미래 leak (token 0이 token 7 평균 받음)
+        # 임시 fallback: FullAttention causal (압축 효율 손실, 안전 우선)
+        return self.full_attn(hidden_states, attention_mask, position_ids, past_key_value, use_cache)
+
+
+# =============================================================================
+# Hybrid Attention (NSA + Differential combined)
+# =============================================================================
+class HybridAttention(nn.Module):
+    """Combine NSA + Differential outputs via learnable gate + final norm (stable).
+
+    Fix v2 (2026-05-05): added post-merge GroupNorm + gate init=0 (sigmoid(0)=0.5 exact balance)
+    + lightly scaled output to prevent 49-layer cumulative divergence.
+    """
+
+    def __init__(self, config: AETHERV27wayConfig, layer_idx: int):
+        super().__init__()
+        self.nsa = NSAAttention(config, layer_idx)
+        self.diff = DifferentialAttention(config, layer_idx)
+        # Per-channel gate (richer than scalar), init to 0 → sigmoid(0)=0.5 exact balance
+        self.gate = nn.Parameter(torch.zeros(config.hidden_size))
+        # FIX 5/8: GroupNorm sequence-spanning leak → RMSNorm (per-token, causal-safe)
+        self.merge_norm = AETHERV27wayRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+
+    def forward(self, hidden_states, attention_mask=None, position_ids=None,
+                past_key_value=None, use_cache=False, **kwargs):
+        nsa_out, kv1 = self.nsa(hidden_states, attention_mask, position_ids, past_key_value, use_cache, **kwargs)
+        diff_out, kv2 = self.diff(hidden_states, attention_mask, position_ids, past_key_value, use_cache, **kwargs)
+        # Per-channel learnable mix: g (sigmoid) per channel
+        g = torch.sigmoid(self.gate)  # shape (hidden_size,)
+        out = g * nsa_out + (1.0 - g) * diff_out
+        # FIX 5/8: per-token RMSNorm (was sequence-spanning GroupNorm = leak)
+        out = self.merge_norm(out)
+        return out, kv1 if kv1 is not None else kv2
+
+
+# =============================================================================
+# 7-aware Attention Dispatcher
+# =============================================================================
+def build_attention(config: AETHERV27wayConfig, layer_idx: int) -> nn.Module:
+    """Pick attention type based on Latin Square index."""
+    attn_type = get_attention_type(layer_idx)
+    if attn_type == "nsa":
+        return NSAAttention(config, layer_idx)
+    elif attn_type == "differential":
+        return DifferentialAttention(config, layer_idx)
+    elif attn_type == "full":
+        return FullAttention(config, layer_idx)
+    elif attn_type == "linear":
+        return LinearAttention(config, layer_idx)
+    elif attn_type == "sliding":
+        return SlidingWindowAttention(config, layer_idx)
+    elif attn_type == "compress":
+        return CompressAttention(config, layer_idx)
+    elif attn_type == "hybrid":
+        return HybridAttention(config, layer_idx)
+    raise ValueError(f"Unknown attention type: {attn_type}")
+
+
+# =============================================================================
+# MoE Block: 25 experts, top-7 active per token
+# =============================================================================
+class AETHERV27wayMLP(nn.Module):
+    """Single expert MLP (SwiGLU)."""
+
+    def __init__(self, config: AETHERV27wayConfig, intermediate_size: Optional[int] = None):
+        super().__init__()
+        self.hidden_size = config.hidden_size
+        self.intermediate_size = intermediate_size or config.expert_intermediate_size
+        self.gate_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
+        self.up_proj = nn.Linear(self.hidden_size, self.intermediate_size, bias=False)
+        self.down_proj = nn.Linear(self.intermediate_size, self.hidden_size, bias=False)
+        self.act_fn = ACT2FN[config.hidden_act]
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        return self.down_proj(self.act_fn(self.gate_proj(x)) * self.up_proj(x))
+
+
+class AETHERV27waySparseMoE(nn.Module):
+    """25-expert MoE with top-7 active routing.
+
+    Each layer has a 5-phase cyclic FFN bias to encode 오행 (Five Elements) cycle.
+    """
+
+    def __init__(self, config: AETHERV27wayConfig, layer_idx: int):
+        super().__init__()
+        self.config = config
+        self.layer_idx = layer_idx
+        self.hidden_size = config.hidden_size
+        self.num_experts = config.num_experts
+        self.top_k = config.num_experts_per_tok
+        self.ffn_phase = get_ffn_phase(layer_idx)  # 0..4 (5-element cycle)
+
+        # Router: hidden → num_experts logits
+        self.gate = nn.Linear(self.hidden_size, self.num_experts, bias=False)
+
+        # 25 experts (each is a SwiGLU MLP)
+        self.experts = nn.ModuleList([
+            AETHERV27wayMLP(config) for _ in range(self.num_experts)
+        ])
+
+        # 오행 cyclic phase bias (learnable, 5 phases)
+        self.phase_bias = nn.Parameter(torch.zeros(5, self.num_experts))
+
+        # Optional shared expert (always active, optional)
+        self.use_shared_expert = getattr(config, "use_shared_expert", True)
+        if self.use_shared_expert:
+            self.shared_expert = AETHERV27wayMLP(
+                config, intermediate_size=config.expert_intermediate_size,
+            )
+            self.shared_expert_gate = nn.Linear(self.hidden_size, 1, bias=False)
+
+    def forward(self, hidden_states: torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor]:
+        bsz, seq_len, dim = hidden_states.shape
+        x = hidden_states.view(-1, dim)  # (bsz*seq, dim)
+
+        # Routing
+        router_logits = self.gate(x)  # (bsz*seq, num_experts)
+        # Add 5-phase cyclic bias (오행)
+        router_logits = router_logits + self.phase_bias[self.ffn_phase].unsqueeze(0)
+
+        # Top-k selection
+        routing_weights, selected_experts = torch.topk(router_logits, self.top_k, dim=-1)
+        routing_weights = F.softmax(routing_weights, dim=-1)
+
+        # Initialize output
+        final_out = torch.zeros_like(x)
+
+        # Per-expert dispatch (loop is OK for prototype; can be optimized with grouped GEMM later)
+        for e in range(self.num_experts):
+            mask = (selected_experts == e)
+            if not mask.any():
+                continue
+            token_idx, k_idx = mask.nonzero(as_tuple=True)
+            expert_in = x[token_idx]
+            expert_out = self.experts[e](expert_in)
+            weight = routing_weights[token_idx, k_idx].unsqueeze(-1).to(expert_out.dtype)
+            final_out.index_add_(0, token_idx, (expert_out * weight).to(final_out.dtype))
+
+        # Shared expert
+        if self.use_shared_expert:
+            shared_out = self.shared_expert(x)
+            shared_gate = torch.sigmoid(self.shared_expert_gate(x))
+            final_out = final_out + (shared_out * shared_gate).to(final_out.dtype)
+
+        final_out = final_out.view(bsz, seq_len, dim)
+        return final_out, router_logits.view(bsz, seq_len, self.num_experts)
+
+
+# =============================================================================
+# Decoder Layer: Attention + MoE FFN with 7-aware + 5-phase logic
+# =============================================================================
+class AETHERV27wayDecoderLayer(nn.Module):
+    def __init__(self, config: AETHERV27wayConfig, layer_idx: int):
+        super().__init__()
+        self.config = config
+        self.layer_idx = layer_idx
+        self.hidden_size = config.hidden_size
+        self.attn_type = get_attention_type(layer_idx)
+        self.ffn_phase = get_ffn_phase(layer_idx)
+
+        # 7-aware attention (1 of 7 types based on Latin square)
+        self.self_attn = build_attention(config, layer_idx)
+
+        # MoE FFN with 5-phase cyclic bias
+        self.mlp = AETHERV27waySparseMoE(config, layer_idx)
+
+        # Norms
+        self.input_layernorm = AETHERV27wayRMSNorm(self.hidden_size, eps=config.rms_norm_eps)
+        self.post_attention_layernorm = AETHERV27wayRMSNorm(self.hidden_size, eps=config.rms_norm_eps)
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        attention_mask: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        past_key_value: Optional[Cache] = None,
+        output_router_logits: bool = False,
+        use_cache: bool = False,
+        **kwargs,
+    ) -> Tuple[torch.Tensor, Optional[Cache], Optional[torch.Tensor]]:
+        # Self-attention with residual
+        residual = hidden_states
+        hidden_states = self.input_layernorm(hidden_states)
+        hidden_states, kv = self.self_attn(
+            hidden_states=hidden_states,
+            attention_mask=attention_mask,
+            position_ids=position_ids,
+            past_key_value=past_key_value,
+            use_cache=use_cache,
+            **kwargs,
+        )
+        hidden_states = residual + hidden_states
+
+        # MoE FFN with residual
+        residual = hidden_states
+        hidden_states = self.post_attention_layernorm(hidden_states)
+        hidden_states, router_logits = self.mlp(hidden_states)
+        hidden_states = residual + hidden_states
+
+        outputs = (hidden_states, kv)
+        if output_router_logits:
+            outputs = outputs + (router_logits,)
+        else:
+            outputs = outputs + (None,)
+        return outputs
+
+
+# =============================================================================
+# Pretrained base
+# =============================================================================
+class AETHERV27wayPreTrainedModel(PreTrainedModel):
+    config_class = AETHERV27wayConfig
+    base_model_prefix = "model"
+    supports_gradient_checkpointing = True
+    _no_split_modules = ["AETHERV27wayDecoderLayer"]
+    _supports_cache_class = True
+    _supports_static_cache = False
+
+    def _init_weights(self, module):
+        std = self.config.initializer_range
+        if isinstance(module, nn.Linear):
+            module.weight.data.normal_(mean=0.0, std=std)
+            if module.bias is not None:
+                module.bias.data.zero_()
+        elif isinstance(module, nn.Embedding):
+            module.weight.data.normal_(mean=0.0, std=std)
+            if module.padding_idx is not None:
+                module.weight.data[module.padding_idx].zero_()
+        elif isinstance(module, AETHERV27wayRMSNorm):
+            module.weight.data.fill_(1.0)
+
+
+# =============================================================================
+# Main Model
+# =============================================================================
+class AETHERV27wayModel(AETHERV27wayPreTrainedModel):
+    """49-layer decoder-only model with 7-aware attention + MoE."""
+
+    def __init__(self, config: AETHERV27wayConfig):
+        super().__init__(config)
+        self.padding_idx = config.pad_token_id
+        self.vocab_size = config.vocab_size
+
+        self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size, self.padding_idx)
+        self.layers = nn.ModuleList([
+            AETHERV27wayDecoderLayer(config, layer_idx) for layer_idx in range(config.num_hidden_layers)
+        ])
+        self.norm = AETHERV27wayRMSNorm(config.hidden_size, eps=config.rms_norm_eps)
+        self.gradient_checkpointing = False
+        self.post_init()
+
+    def get_input_embeddings(self):
+        return self.embed_tokens
+
+    def set_input_embeddings(self, value):
+        self.embed_tokens = value
+
+    def forward(
+        self,
+        input_ids: Optional[torch.LongTensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        past_key_values: Optional[Cache] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        use_cache: Optional[bool] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        output_router_logits: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+        **kwargs,
+    ) -> Union[Tuple, MoeModelOutputWithPast]:
+        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
+        output_hidden_states = output_hidden_states if output_hidden_states is not None else False
+        output_router_logits = output_router_logits if output_router_logits is not None else self.config.output_router_logits
+        use_cache = use_cache if use_cache is not None else self.config.use_cache
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
+        if input_ids is not None and inputs_embeds is not None:
+            raise ValueError("Cannot specify both input_ids and inputs_embeds")
+        if input_ids is not None:
+            bsz, seq_len = input_ids.shape
+        elif inputs_embeds is not None:
+            bsz, seq_len, _ = inputs_embeds.shape
+        else:
+            raise ValueError("Either input_ids or inputs_embeds must be provided")
+
+        if inputs_embeds is None:
+            inputs_embeds = self.embed_tokens(input_ids)
+
+        # TST superposition: bag s consecutive token-embeddings (FSDP-safe)
+        _tst_bag = kwargs.get("tst_bag_size", 0)
+        if _tst_bag and _tst_bag > 1:
+            _b, _l, _d = inputs_embeds.shape
+            inputs_embeds = inputs_embeds.view(_b, _l // _tst_bag, _tst_bag, _d).mean(dim=2)
+            seq_len = inputs_embeds.shape[1]
+
+        if use_cache and past_key_values is None:
+            past_key_values = DynamicCache()
+
+        past_seen = past_key_values.get_seq_length() if past_key_values is not None else 0
+
+        if position_ids is None:
+            position_ids = torch.arange(
+                past_seen, past_seen + seq_len, device=inputs_embeds.device,
+            ).unsqueeze(0)
+
+        hidden_states = inputs_embeds
+
+        all_hidden_states = () if output_hidden_states else None
+        all_router_logits = () if output_router_logits else None
+
+        for layer_idx, decoder_layer in enumerate(self.layers):
+            if output_hidden_states:
+                all_hidden_states += (hidden_states,)
+
+            if self.gradient_checkpointing and self.training:
+                layer_out = self._gradient_checkpointing_func(
+                    decoder_layer.__call__,
+                    hidden_states, attention_mask, position_ids,
+                    past_key_values, output_router_logits, use_cache,
+                )
+            else:
+                layer_out = decoder_layer(
+                    hidden_states=hidden_states,
+                    attention_mask=attention_mask,
+                    position_ids=position_ids,
+                    past_key_value=past_key_values,
+                    output_router_logits=output_router_logits,
+                    use_cache=use_cache,
+                )
+
+            hidden_states = layer_out[0]
+            if output_router_logits:
+                all_router_logits += (layer_out[2],)
+
+        hidden_states = self.norm(hidden_states)
+        if output_hidden_states:
+            all_hidden_states += (hidden_states,)
+
+        if not return_dict:
+            return tuple(v for v in [
+                hidden_states, past_key_values, all_hidden_states, None, all_router_logits,
+            ] if v is not None)
+
+        return MoeModelOutputWithPast(
+            last_hidden_state=hidden_states,
+            past_key_values=past_key_values,
+            hidden_states=all_hidden_states,
+            attentions=None,
+            router_logits=all_router_logits,
+        )
+
+
+# =============================================================================
+# Causal LM Wrapper
+# =============================================================================
+class AETHERV27wayForCausalLM(AETHERV27wayPreTrainedModel):
+    _tied_weights_keys = ["lm_head.weight"]
+
+    def __init__(self, config: AETHERV27wayConfig):
+        super().__init__(config)
+        self.model = AETHERV27wayModel(config)
+        self.vocab_size = config.vocab_size
+        self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
+        self.router_aux_loss_coef = getattr(config, "router_aux_loss_coef", 0.001)
+        self.num_experts = config.num_experts
+        self.num_experts_per_tok = config.num_experts_per_tok
+        self.post_init()
+
+    def get_input_embeddings(self):
+        return self.model.embed_tokens
+
+    def set_input_embeddings(self, value):
+        self.model.embed_tokens = value
+
+    def get_output_embeddings(self):
+        return self.lm_head
+
+    def set_output_embeddings(self, new_embeddings):
+        self.lm_head = new_embeddings
+
+    def get_decoder(self):
+        return self.model
+
+    def forward(
+        self,
+        input_ids: Optional[torch.LongTensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        past_key_values: Optional[Cache] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        labels: Optional[torch.LongTensor] = None,
+        use_cache: Optional[bool] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        output_router_logits: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+        **kwargs,
+    ) -> Union[Tuple, MoeCausalLMOutputWithPast]:
+        output_router_logits = output_router_logits if output_router_logits is not None else self.config.output_router_logits
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
+        outputs = self.model(
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            position_ids=position_ids,
+            past_key_values=past_key_values,
+            inputs_embeds=inputs_embeds,
+            use_cache=use_cache,
+            output_hidden_states=output_hidden_states,
+            output_router_logits=output_router_logits,
+            tst_bag_size=kwargs.get("tst_bag_size", 0),
+            return_dict=True,
+        )
+        hidden_states = outputs.last_hidden_state
+        logits = self.lm_head(hidden_states).float()
+
+        loss = None
+        aux_loss = None
+        if labels is not None:
+            shift_logits = logits[..., :-1, :].contiguous()
+            shift_labels = labels[..., 1:].contiguous()
+            loss = F.cross_entropy(
+                shift_logits.view(-1, self.vocab_size),
+                shift_labels.view(-1),
+                ignore_index=-100,
+            )
+
+        if output_router_logits and outputs.router_logits is not None:
+            aux_loss = self._compute_router_aux_loss(outputs.router_logits, attention_mask)
+            if loss is not None:
+                loss = loss + self.router_aux_loss_coef * aux_loss
+
+        if not return_dict:
+            output = (logits,) + tuple(v for v in [
+                outputs.past_key_values, outputs.hidden_states, None, outputs.router_logits, aux_loss,
+            ] if v is not None)
+            return (loss,) + output if loss is not None else output
+
+        return MoeCausalLMOutputWithPast(
+            loss=loss,
+            aux_loss=aux_loss,
+            logits=logits,
+            past_key_values=outputs.past_key_values,
+            hidden_states=outputs.hidden_states,
+            attentions=None,
+            router_logits=outputs.router_logits,
+        )
+
+    def _compute_router_aux_loss(self, router_logits: Tuple[torch.Tensor, ...], attention_mask=None):
+        """Standard switch-transformer auxiliary loss for load balancing."""
+        if router_logits is None or len(router_logits) == 0:
+            return None
+        # Each router_logits[i] shape: (bsz, seq, num_experts) → flatten to (n_tokens, num_experts)
+        flat = []
+        for r in router_logits:
+            if r is None:
+                continue
+            flat.append(r.reshape(-1, self.num_experts))
+        if not flat:
+            return None
+        all_router_logits = torch.cat(flat, dim=0)  # (total_tokens, num_experts)
+
+        routing_weights = F.softmax(all_router_logits.float(), dim=-1)
+        _, selected_experts = torch.topk(routing_weights, self.num_experts_per_tok, dim=-1)
+
+        # Expert mask: (n_tokens, top_k, num_experts)
+        expert_mask = F.one_hot(selected_experts, num_classes=self.num_experts).float()
+        # Tokens-per-expert frequency: average over (n_tokens, top_k) dims → (num_experts,)
+        tokens_per_expert = expert_mask.mean(dim=(0, 1))
+        # Router prob per expert: (num_experts,)
+        router_prob_per_expert = routing_weights.mean(dim=0)
+        # aux_loss = num_experts * sum(token_freq * prob)
+        return self.num_experts * torch.sum(tokens_per_expert * router_prob_per_expert)
+
+    def prepare_inputs_for_generation(
+        self,
+        input_ids,
+        past_key_values=None,
+        attention_mask=None,
+        inputs_embeds=None,
+        **kwargs,
+    ):
+        if past_key_values is not None:
+            input_ids = input_ids[:, -1:]
+        position_ids = kwargs.get("position_ids", None)
+        if attention_mask is not None and position_ids is None:
+            position_ids = attention_mask.long().cumsum(-1) - 1
+            position_ids.masked_fill_(attention_mask == 0, 1)
+            if past_key_values is not None:
+                position_ids = position_ids[:, -input_ids.shape[1]:]
+        return {
+            "input_ids": input_ids,
+            "position_ids": position_ids,
+            "past_key_values": past_key_values,
+            "use_cache": kwargs.get("use_cache"),
+            "attention_mask": attention_mask,
+        }
+
+
+# =============================================================================
+# Helper: Latin Square Layer Map (for analysis / debugging)
+# =============================================================================
+def print_layer_map(num_layers: int = 49):
+    """Print the Latin Square attention type map."""
+    print(f"=== AETHER-V2-7way Layer Map ({num_layers} layers) ===")
+    for L in range(num_layers):
+        attn = get_attention_type(L)
+        phase = get_ffn_phase(L)
+        row = L // 7
+        col = L % 7
+        print(f"  L{L:02d} (row={row} col={col}): attn={attn:12s} ffn_phase={phase}")
+
+
+__all__ = [
+    "AETHERV27wayConfig",
+    "AETHERV27wayModel",
+    "AETHERV27wayForCausalLM",
+    "AETHERV27wayPreTrainedModel",
+    "AETHERV27wayDecoderLayer",
+    "AETHERV27waySparseMoE",
+    "build_attention",
+    "get_attention_type",
+    "get_ffn_phase",
+    "LATIN_SQUARE_7x7",
+    "ATTN_TYPES",
+    "print_layer_map",
+]