model.py

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

dml = torch_directml.device()
torch.device(dml)

stoi = {ch: i for i, ch in enumerate(config.chars)}
itos = {i: ch for i, ch in enumerate(config.chars)}


def encode(x):
    return [stoi[ch] for ch in x]


def decode(x):
    return ''.join([itos[ch] for ch in x])


class Head(nn.Module):

    def __init__(self, head_size):
        super().__init__()
        self.key = nn.Linear(config.n_embd, head_size, bias=False)
        self.query = nn.Linear(config.n_embd, head_size, bias=False)
        self.value = nn.Linear(config.n_embd, head_size, bias=False)
        self.register_buffer('tril', torch.tril(torch.ones(config.block_size, config.block_size)))
        self.dropout = nn.Dropout(config.dropout)

    def forward(self, x):
        B, T, C = x.shape
        k = self.key(x)
        q = self.query(x)

        wei = q @ k.transpose(-2, -1) * C ** -0.5
        wei = wei.masked_fill(self.tril[:T, :T] == 0, float('-inf'))
        wei = F.softmax(wei, dim=-1)
        wei = self.dropout(wei)

        v = self.value(x)
        out = wei @ v
        return out


class MultiHeadAttention(nn.Module):

    def __init__(self, num_heads, head_size):
        super().__init__()
        self.heads = nn.ModuleList([Head(head_size) for _ in range(num_heads)]).to(dml)
        self.proj = nn.Linear(config.n_embd, config.n_embd)
        self.dropout = nn.Dropout(config.dropout)

    def forward(self, x):
        out = torch.cat([head(x) for head in self.heads], dim=-1)
        out = self.proj(out)
        out = self.dropout(out)
        return out


class FeedForward(nn.Module):

    def __init__(self):
        super().__init__()
        self.net = nn.Sequential(
            nn.Linear(config.n_embd, 4 * config.n_embd),
            nn.ReLU(),
            nn.Linear(4 * config.n_embd, config.n_embd),
            nn.Dropout(config.dropout)
        )

    def forward(self, x):
        return self.net(x)


class Block(nn.Module):

    def __init__(self):
        super().__init__()
        head_size = config.n_embd // config.n_head
        self.sa = MultiHeadAttention(config.n_head, head_size)
        self.ffwd = FeedForward()
        self.ln1 = nn.LayerNorm(config.n_embd)
        self.ln2 = nn.LayerNorm(config.n_embd)

    def forward(self, x):
        x = x + self.sa(self.ln1(x))
        x = x + self.ffwd(self.ln2(x))
        return x


class BigramLanguageModel(nn.Module):

    def __init__(self):
        super().__init__()
        self.token_embedding_table = nn.Embedding(config.vocab_size, config.n_embd)
        self.position_embedding_table = nn.Embedding(config.block_size, config.n_embd)
        self.blocks = nn.Sequential(*[Block() for _ in range(config.n_layer)])
        self.ln_f = nn.LayerNorm(config.n_embd)
        self.lm_head = nn.Linear(config.n_embd, config.vocab_size)

    def forward(self, idx, targets=None):
        B, T = idx.shape

        tok_emb = self.token_embedding_table(idx)
        pos_emb = self.position_embedding_table(torch.arange(T, device=dml))
        x = tok_emb + pos_emb
        x = self.blocks(x)
        x = self.ln_f(x)
        logits = self.lm_head(x)

        loss = None
        if targets is not None:
            B, T, C = logits.shape
            logits = logits.view(B * T, C)
            targets = targets.view(B * T)
            loss = F.cross_entropy(logits, targets)

        return logits, loss

    def generate(self, idx, max_new_tokens):
        for _ in range(max_new_tokens):
            idx_cond = idx[:, -config.block_size:]
            logits, loss = self(idx_cond)
            logits = logits[:, -1, :]
            probs = F.softmax(logits, dim=-1)
            idx_next = torch.multinomial(probs, num_samples=1)
            idx = torch.cat([idx, idx_next], dim=1)
        return idx