model.py

import math
import inspect
import torch
import torch.nn as nn
from torch.nn import functional as F
from dataclasses import dataclass

@dataclass
class GPTConfig:
    block_size: int = 256
    vocab_size: int = 65
    n_layer: int = 6
    n_head: int = 6
    n_embd: int = 384
    dropout: float = 0.2
    bias: bool = False

class CausalSelfAttention(nn.Module):
    def __init__(self, config):
        super().__init__()
        assert config.n_embd % config.n_head == 0
        self.c_attn = nn.Linear(config.n_embd, 3 * config.n_embd, bias=config.bias)
        self.c_proj = nn.Linear(config.n_embd, config.n_embd, bias=config.bias)
        self.attn_dropout = nn.Dropout(config.dropout)
        self.resid_dropout = nn.Dropout(config.dropout)
        self.n_head = config.n_head
        self.n_embd = config.n_embd

    def forward(self, x):
        B, T, C = x.size()
        qkv = self.c_attn(x)
        q, k, v = qkv.split(self.n_embd, dim=2)
        k = k.view(B, T, self.n_head, C // self.n_head).transpose(1, 2)
        q = q.view(B, T, self.n_head, C // self.n_head).transpose(1, 2)
        v = v.view(B, T, self.n_head, C // self.n_head).transpose(1, 2)
        
        # PyTorch 2.0 Flash Attention
        y = F.scaled_dot_product_attention(q, k, v, is_causal=True, dropout_p=self.attn_dropout.p if self.training else 0)
        y = y.transpose(1, 2).contiguous().view(B, T, C)
        return self.resid_dropout(self.c_proj(y))

class MLP(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.c_fc    = nn.Linear(config.n_embd, 4 * config.n_embd, bias=config.bias)
        self.gelu    = nn.GELU()
        self.c_proj  = nn.Linear(4 * config.n_embd, config.n_embd, bias=config.bias)
        self.dropout = nn.Dropout(config.dropout)

    def forward(self, x):
        return self.dropout(self.c_proj(self.gelu(self.c_fc(x))))


class Block(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.ln_1 = nn.LayerNorm(config.n_embd, bias=config.bias)
        self.attn = CausalSelfAttention(config)
        self.ln_2 = nn.LayerNorm(config.n_embd, bias=config.bias)
        self.mlp = MLP(config)

    def forward(self, x):
        x = x + self.attn(self.ln_1(x))
        x = x + self.mlp(self.ln_2(x))
        return x

class GPT(nn.Module):
    def __init__(self, config):
        super().__init__()
        self.config = config
        self.transformer = nn.ModuleDict(dict(
            wte = nn.Embedding(config.vocab_size, config.n_embd),
            wpe = nn.Embedding(config.block_size, config.n_embd),
            drop = nn.Dropout(config.dropout),
            h = nn.ModuleList([Block(config) for _ in range(config.n_layer)]),
            ln_f = nn.LayerNorm(config.n_embd, bias=config.bias),
        ))
        self.lm_head = nn.Linear(config.n_embd, config.vocab_size, bias=False)
        self.transformer.wte.weight = self.lm_head.weight # Weight tying
        self.apply(self._init_weights)

        # Apply special scaled init to the residual projections (per GPT-2 paper)
        for pn, p in self.named_parameters():
            if pn.endswith('c_proj.weight'):
                torch.nn.init.normal_(p, mean=0.0, std=0.02 / math.sqrt(2 * config.n_layer))

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

    def forward(self, idx, targets=None):
        device = idx.device
        b, t = idx.size()
        pos = torch.arange(0, t, dtype=torch.long, device=device)
        
        x = self.transformer.wte(idx) + self.transformer.wpe(pos)
        x = self.transformer.drop(x)
        for block in self.transformer.h:
            x = block(x)
        x = self.transformer.ln_f(x)
        
        if targets is not None:
            logits = self.lm_head(x)
            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1))
            return logits, loss
        return self.lm_head(x[:, [-1], :]), None

    @torch.no_grad()
    def generate(self, idx, max_new_tokens, temperature=1.0, top_k=None):
        for _ in range(max_new_tokens):
            idx_cond = idx if idx.size(1) <= self.config.block_size else idx[:, -self.config.block_size:]
            logits, _ = self(idx_cond)
            logits = logits[:, -1, :] / temperature
            if top_k is not None:
                v, _ = torch.topk(logits, min(top_k, logits.size(-1)))
                logits[logits < v[:, [-1]]] = -float('Inf')
            probs = F.softmax(logits, dim=-1)
            idx_next = torch.multinomial(probs, num_samples=1)
            idx = torch.cat((idx, idx_next), dim=1)
        return idx

    def configure_optimizers(self, weight_decay, learning_rate, betas, device_type):
        # start with all of the candidate parameters
        param_dict = {pn: p for pn, p in self.named_parameters()}
        # filter out those that do not require grad
        param_dict = {pn: p for pn, p in param_dict.items() if p.requires_grad}
        # create optim groups. Any parameters that is 2D will be weight decayed, otherwise no.
        # i.e. all weight tensors in matmuls + embeddings decay, all biases and layernorms don't.
        decay_params = [p for n, p in param_dict.items() if p.dim() >= 2]
        nodecay_params = [p for n, p in param_dict.items() if p.dim() < 2]
        optim_groups = [
            {'params': decay_params, 'weight_decay': weight_decay},
            {'params': nodecay_params, 'weight_decay': 0.0}
        ]
        num_decay_params = sum(p.numel() for p in decay_params)
        num_nodecay_params = sum(p.numel() for p in nodecay_params)
        print(f"num decayed parameter tensors: {len(decay_params)}, with {num_decay_params:,} parameters")
        print(f"num non-decayed parameter tensors: {len(nodecay_params)}, with {num_nodecay_params:,} parameters")
        # Create AdamW optimizer and use the fused version if it is available
        fused_available = 'fused' in inspect.signature(torch.optim.AdamW).parameters
        use_fused = fused_available and device_type == 'cuda'
        extra_args = dict(fused=True) if use_fused else dict()
        optimizer = torch.optim.AdamW(optim_groups, lr=learning_rate, betas=betas, **extra_args)
        print(f"using fused AdamW: {use_fused}")

        return optimizer