model.py

from __future__ import annotations
import math
import torch
import torch.nn as nn
import torch.nn.functional as F

class RMSNorm(nn.Module):

    def __init__(self, dim, eps=1e-06):
        super().__init__()
        self.eps = eps
        self.weight = nn.Parameter(torch.ones(dim))

    def forward(self, x):
        dtype = x.dtype
        x = x.float()
        x = x * torch.rsqrt(x.pow(2).mean(-1, keepdim=True) + self.eps)
        return x.to(dtype) * self.weight

def rope_freqs(seq_len, head_dim, theta=100000.0, device=None):
    inv_freq = 1.0 / theta ** (torch.arange(0, head_dim, 2, device=device).float() / head_dim)
    t = torch.arange(seq_len, device=device).float()
    freqs = torch.outer(t, inv_freq)
    return torch.cat([freqs, freqs], dim=-1)

def rotate_half(x):
    x1, x2 = x.chunk(2, dim=-1)
    return torch.cat([-x2, x1], dim=-1)

def apply_rope(x, cos, sin):
    return x * cos + rotate_half(x) * sin

class Attention(nn.Module):

    def __init__(self, dim, n_heads, n_kv_heads, head_dim, qk_norm_eps=1e-06):
        super().__init__()
        if n_heads % n_kv_heads != 0:
            raise ValueError(f'n_heads ({n_heads}) must be divisible by n_kv_heads ({n_kv_heads}); valid choices for {n_heads} heads: {[k for k in range(1, n_heads + 1) if n_heads % k == 0]}')
        self.n_heads = n_heads
        self.n_kv_heads = n_kv_heads
        self.head_dim = head_dim
        self.n_rep = n_heads // n_kv_heads
        self.q_proj = nn.Linear(dim, n_heads * head_dim, bias=False)
        self.k_proj = nn.Linear(dim, n_kv_heads * head_dim, bias=False)
        self.v_proj = nn.Linear(dim, n_kv_heads * head_dim, bias=False)
        self.o_proj = nn.Linear(n_heads * head_dim, dim, bias=False)
        self.q_norm = RMSNorm(head_dim, eps=qk_norm_eps)
        self.k_norm = RMSNorm(head_dim, eps=qk_norm_eps)

    def forward(self, x, cos, sin):
        B, T, _ = x.shape
        q = self.q_proj(x).view(B, T, self.n_heads, self.head_dim)
        k = self.k_proj(x).view(B, T, self.n_kv_heads, self.head_dim)
        v = self.v_proj(x).view(B, T, self.n_kv_heads, self.head_dim)
        q = self.q_norm(q)
        k = self.k_norm(k)
        q = apply_rope(q, cos, sin)
        k = apply_rope(k, cos, sin)
        q = q.transpose(1, 2)
        k = k.transpose(1, 2).repeat_interleave(self.n_rep, dim=1)
        v = v.transpose(1, 2).repeat_interleave(self.n_rep, dim=1)
        out = F.scaled_dot_product_attention(q, k, v, is_causal=True)
        out = out.transpose(1, 2).contiguous().view(B, T, -1)
        return self.o_proj(out)

class SwiGLU(nn.Module):

    def __init__(self, dim, hidden):
        super().__init__()
        self.gate_proj = nn.Linear(dim, hidden, bias=False)
        self.up_proj = nn.Linear(dim, hidden, bias=False)
        self.down_proj = nn.Linear(hidden, dim, bias=False)

    def forward(self, x):
        return self.down_proj(F.silu(self.gate_proj(x)) * self.up_proj(x))

class DecoderLayer(nn.Module):

    def __init__(self, dim, n_heads, n_kv_heads, head_dim, mlp_hidden, norm_eps=1e-06):
        super().__init__()
        self.attn_norm = RMSNorm(dim, eps=norm_eps)
        self.attn = Attention(dim, n_heads, n_kv_heads, head_dim)
        self.mlp_norm = RMSNorm(dim, eps=norm_eps)
        self.mlp = SwiGLU(dim, mlp_hidden)

    def forward(self, x, cos, sin):
        x = x + self.attn(self.attn_norm(x), cos, sin)
        x = x + self.mlp(self.mlp_norm(x))
        return x

class LogosModel(nn.Module):

    def __init__(self, vocab_size=32768, dim=640, n_layers=30, n_heads=10, n_kv_heads=5, mlp_hidden=1728, max_seq_len=4096, rope_theta=100000.0, norm_eps=1e-06, tie_embeddings=True):
        super().__init__()
        self.dim = dim
        self.n_layers = n_layers
        self.head_dim = dim // n_heads
        self.max_seq_len = max_seq_len
        self.rope_theta = rope_theta
        self.embed_tokens = nn.Embedding(vocab_size, dim)
        self.layers = nn.ModuleList([DecoderLayer(dim, n_heads, n_kv_heads, self.head_dim, mlp_hidden, norm_eps) for _ in range(n_layers)])
        self.norm_out = RMSNorm(dim, eps=norm_eps)
        self.lm_head = nn.Linear(dim, vocab_size, bias=False)
        if tie_embeddings:
            self.lm_head.weight = self.embed_tokens.weight
        self.apply(self._init_weights)
        for layer in self.layers:
            nn.init.normal_(layer.mlp.down_proj.weight, mean=0.0, std=0.02 / math.sqrt(2 * n_layers))
            nn.init.normal_(layer.attn.o_proj.weight, mean=0.0, std=0.02 / math.sqrt(2 * n_layers))
        cos, sin = self._build_rope_cache(max_seq_len)
        self.register_buffer('rope_cos', cos, persistent=False)
        self.register_buffer('rope_sin', sin, persistent=False)

    def _init_weights(self, m):
        if isinstance(m, nn.Linear):
            nn.init.normal_(m.weight, mean=0.0, std=0.02)
            if m.bias is not None:
                nn.init.zeros_(m.bias)
        elif isinstance(m, nn.Embedding):
            nn.init.normal_(m.weight, mean=0.0, std=0.02)

    def _build_rope_cache(self, seq_len):
        freqs = rope_freqs(seq_len, self.head_dim, self.rope_theta)
        return (freqs.cos()[None, :, None, :], freqs.sin()[None, :, None, :])

    def forward(self, input_ids, labels=None, loss_chunk_size=2048):
        B, T = input_ids.shape
        x = self.embed_tokens(input_ids)
        cos = self.rope_cos[:, :T].to(x.dtype)
        sin = self.rope_sin[:, :T].to(x.dtype)
        for layer in self.layers:
            x = layer(x, cos, sin)
        x = self.norm_out(x)
        if labels is None:
            return (self.lm_head(x), None)
        shift_x = x[:, :-1].reshape(-1, x.size(-1))
        shift_labels = labels[:, 1:].reshape(-1)
        n = shift_x.size(0)
        total_loss = x.new_zeros((), dtype=torch.float32)
        total_count = x.new_zeros((), dtype=torch.float32)
        for start in range(0, n, loss_chunk_size):
            end = min(start + loss_chunk_size, n)
            chunk_labels = shift_labels[start:end]
            valid = chunk_labels != -100
            count = valid.sum()
            if count == 0:
                continue
            chunk_logits = self.lm_head(shift_x[start:end]).float()
            chunk_loss = F.cross_entropy(chunk_logits, chunk_labels, ignore_index=-100, reduction='sum')
            total_loss = total_loss + chunk_loss
            total_count = total_count + count
        loss = total_loss / total_count.clamp(min=1)
        return (None, loss)

    def num_params(self, exclude_embeddings=False):
        n = sum((p.numel() for p in self.parameters()))
        if exclude_embeddings:
            n -= self.embed_tokens.weight.numel()
            if self.lm_head.weight is not self.embed_tokens.weight:
                n -= self.lm_head.weight.numel()
        return n
if __name__ == '__main__':
    m = LogosModel()
    print(f'total params: {m.num_params():,}')
    print(f'non-embedding params: {m.num_params(exclude_embeddings=True):,}')
    x = torch.randint(0, 32768, (2, 128))
    logits, loss = m(x, labels=x)
    print('loss:', loss.item() if loss is not None else None)
    logits, _ = m(x)
    print('logits shape (no labels):', logits.shape)