models/transformer_encoder.py

"""
Modified from nanoGPT: https://github.com/karpathy/nanoGPT/blob/master/model.py

Full definition of a GPT Language Model, all of it in this single file.
References:
1) the official GPT-2 TensorFlow implementation released by OpenAI:
https://github.com/openai/gpt-2/blob/master/src/model.py
2) huggingface/transformers PyTorch implementation:
https://github.com/huggingface/transformers/blob/main/src/transformers/models/gpt2/modeling_gpt2.py
"""

import math
import inspect
import logging
from dataclasses import dataclass

import torch
import torch.nn as nn
from torch.nn import functional as F


class LayerNorm(nn.Module):
    """LayerNorm but with an optional bias. PyTorch doesn't support simply bias=False"""

    def __init__(self, ndim, bias):
        super().__init__()
        self.weight = nn.Parameter(torch.ones(ndim))
        self.bias = nn.Parameter(torch.zeros(ndim)) if bias else None

    def forward(self, input):
        return F.layer_norm(input, self.weight.shape, self.weight, self.bias, 1e-5)


class CausalSelfAttention(nn.Module):
    def __init__(self, config):
        super().__init__()
        assert config.n_embd % config.n_head == 0
        # key, query, value projections for all heads, but in a batch
        self.c_attn = nn.Linear(config.n_embd, 3 * config.n_embd, bias=config.bias)
        # output projection
        self.c_proj = nn.Linear(config.n_embd, config.n_embd, bias=config.bias)
        # regularization
        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
        self.dropout = config.dropout
        # flash attention make GPU go brrrrr but support is only in PyTorch >= 2.0
        self.flash = hasattr(torch.nn.functional, "scaled_dot_product_attention")
        if not self.flash:
            logging.warn(
                "Using slow attention. Flash Attention requires PyTorch >= 2.0"
            )
            # causal mask to ensure that attention is only applied to the left in the input sequence
            self.register_buffer(
                "bias",
                torch.tril(torch.ones(config.block_size, config.block_size)).view(
                    1, 1, config.block_size, config.block_size
                ),
            )

    def forward(self, x):
        (
            B,
            T,
            C,
        ) = x.size()  # batch size, sequence length, embedding dimensionality (n_embd)

        # calculate query, key, values for all heads in batch and move head forward to be the batch dim
        q, k, v = self.c_attn(x).split(self.n_embd, dim=2)
        k = k.view(B, T, self.n_head, C // self.n_head).transpose(
            1, 2
        )  # (B, nh, T, hs)
        q = q.view(B, T, self.n_head, C // self.n_head).transpose(
            1, 2
        )  # (B, nh, T, hs)
        v = v.view(B, T, self.n_head, C // self.n_head).transpose(
            1, 2
        )  # (B, nh, T, hs)

        # causal self-attention; Self-attend: (B, nh, T, hs) x (B, nh, hs, T) -> (B, nh, T, T)
        if self.flash:
            # efficient attention using Flash Attention CUDA kernels
            y = torch.nn.functional.scaled_dot_product_attention(
                q,
                k,
                v,
                attn_mask=None,
                dropout_p=self.dropout if self.training else 0,
                is_causal=True,
            )
        else:
            # manual implementation of attention
            att = (q @ k.transpose(-2, -1)) * (1.0 / math.sqrt(k.size(-1)))
            att = att.masked_fill(self.bias[:, :, :T, :T] == 0, float("-inf"))
            att = F.softmax(att, dim=-1)
            att = self.attn_dropout(att)
            y = att @ v  # (B, nh, T, T) x (B, nh, T, hs) -> (B, nh, T, hs)
        y = (
            y.transpose(1, 2).contiguous().view(B, T, C)
        )  # re-assemble all head outputs side by side

        # output projection
        y = self.resid_dropout(self.c_proj(y))
        return 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):
        x = self.c_fc(x)
        x = self.gelu(x)
        x = self.c_proj(x)
        x = self.dropout(x)
        return x


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


@dataclass
class TransformerEncoderConfig:
    block_size: int = 10  # length of sequence
    input_dim: int = 512
    n_layer: int = 3
    n_head: int = 4
    n_embd: int = 256
    output_dim: int = 512
    dropout: float = 0.0
    bias: bool = True  # True: bias in Linears and LayerNorms, like GPT-2. False: a bit better and faster


class TransformerEncoder(nn.Module):
    def __init__(self, config):
        super().__init__()
        assert config.input_dim is not None
        assert config.block_size is not None
        self.config = config

        self.transformer = nn.ModuleDict(
            dict(
                wte=nn.Linear(config.input_dim, 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=LayerNorm(config.n_embd, bias=config.bias),
            )
        )
        self.output_head = nn.Linear(config.n_embd, config.output_dim, bias=True)

        # init all weights
        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)
                )

        # report number of parameters
        logging.info("number of parameters: %.2fM" % (self.get_num_params() / 1e6,))

    def get_num_params(self, non_embedding=True):
        """
        Return the number of parameters in the model.
        For non-embedding count (default), the position embeddings get subtracted.
        The token embeddings would too, except due to the parameter sharing these
        params are actually used as weights in the final layer, so we include them.
        """
        n_params = sum(p.numel() for p in self.parameters())
        if non_embedding:
            n_params -= self.transformer.wpe.weight.numel()
        return n_params

    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, x, target=None):
        device = x.device
        b, t, d = x.size()
        assert (
            t <= self.config.block_size
        ), f"Cannot forward sequence of length {t}, block size is only {self.config.block_size}"
        pos = torch.arange(0, t, dtype=torch.long, device=device)  # shape (t)

        # forward the GPT model itself
        tok_emb = self.transformer.wte(x)  # token embeddings of shape (b, t, n_embd)
        pos_emb = self.transformer.wpe(pos)  # position embeddings of shape (t, n_embd)
        x = self.transformer.drop(tok_emb + pos_emb)
        for block in self.transformer.h:
            x = block(x)
        x = self.transformer.ln_f(x)

        output = self.output_head(x)
        loss = None if target is None else F.mse_loss(output, target)
        if target is None:
            return output
        else:
            return output, loss

    def configure_optimizers(self, weight_decay, lr, betas, device_type=None):
        # 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)
        logging.info(
            f"num decayed parameter tensors: {len(decay_params)}, with {num_decay_params:,} parameters"
        )
        logging.info(
            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=lr, betas=betas, **extra_args)
        logging.info(f"using fused AdamW: {use_fused}")

        return optimizer