modeling.py

"""TinyStoriesGPT — 24.59M-param BPE GPT trained on roneneldan/TinyStories.
Architecture: weight-tied decoder-only GPT, RMSNorm, fused qkv, GELU FFN.
Not a transformers model — load with this class + safetensors.
"""
import torch
import torch.nn as nn
import torch.nn.functional as F

class RMSNorm(nn.Module):
    def __init__(self, d):
        super().__init__()
        self.w = nn.Parameter(torch.ones(d))
    def forward(self, x):
        return self.w * x * torch.rsqrt(x.float().pow(2).mean(-1, keepdim=True) + 1e-6)

class Block(nn.Module):
    def __init__(self, d, h, ffn):
        super().__init__()
        self.ln1 = RMSNorm(d)
        self.ln2 = RMSNorm(d)
        self.qkv = nn.Linear(d, 3*d, bias=False)
        self.proj = nn.Linear(d, d, bias=False)
        self.fc1 = nn.Linear(d, ffn, bias=False)
        self.fc2 = nn.Linear(ffn, d, bias=False)
        self.h, self.d = h, d
    def forward(self, x):
        B, T, D = x.shape
        h = self.ln1(x)
        qkv = self.qkv(h).view(B, T, 3, self.h, D//self.h).transpose(2,1)
        q, k, v = qkv[:,0], qkv[:,1], qkv[:,2]
        q, k, v = q.transpose(1,2), k.transpose(1,2), v.transpose(1,2)
        att = F.scaled_dot_product_attention(q, k, v, is_causal=True)
        att = att.transpose(1,2).reshape(B, T, D)
        x = x + self.proj(att)
        x = x + self.fc2(F.gelu(self.fc1(self.ln2(x))))
        return x

class TinyStoriesGPT(nn.Module):
    def __init__(self, vocab_size=8192, d=384, n_layers=12, n_heads=8, ffn=1536, seq=512):
        super().__init__()
        self.tok = nn.Embedding(vocab_size, d)
        self.pos = nn.Embedding(seq, d)
        self.blocks = nn.ModuleList([Block(d, n_heads, ffn) for _ in range(n_layers)])
        self.ln_f = RMSNorm(d)
        self.vocab_size = vocab_size
    def forward(self, x, targets=None):
        b, t = x.shape
        h = self.tok(x) + self.pos(torch.arange(t, device=x.device))
        for blk in self.blocks:
            h = blk(h)
        h = self.ln_f(h)
        logits = h @ self.tok.weight.t()
        if targets is not None:
            return F.cross_entropy(logits.float().view(-1, self.vocab_size), targets.view(-1))
        return logits
    @classmethod
    def from_pretrained(cls, path, device="cpu"):
        import json
        from safetensors.torch import load_file
        cfg = json.load(open(f"{path}/config.json"))
        model = cls(vocab_size=cfg["vocab_size"], d=cfg["D"], n_layers=cfg["L"],
                    n_heads=cfg["H"], ffn=cfg["FFN"], seq=cfg["max_position_embeddings"])
        sd = load_file(f"{path}/model.safetensors")
        model.load_state_dict(sd)
        model = model.to(device).eval()
        return model