"""A very small GPT-style language model (character level)."""
import torch
import torch.nn as nn
import torch.nn.functional as F


class Block(nn.Module):
    """One transformer block: self-attention, then a small feed-forward net."""

    def __init__(self, n_embd, n_head, dropout):
        super().__init__()
        self.n_head = n_head
        self.ln1 = nn.LayerNorm(n_embd)
        self.qkv = nn.Linear(n_embd, 3 * n_embd)
        self.proj = nn.Linear(n_embd, n_embd)
        self.ln2 = nn.LayerNorm(n_embd)
        self.mlp = nn.Sequential(
            nn.Linear(n_embd, 4 * n_embd), nn.GELU(), nn.Linear(4 * n_embd, n_embd)
        )
        self.dropout = dropout

    def forward(self, x):
        B, T, C = x.shape
        q, k, v = self.qkv(self.ln1(x)).split(C, dim=2)
        q, k, v = (t.view(B, T, self.n_head, C // self.n_head).transpose(1, 2) for t in (q, k, v))
        # is_causal=True: each character may only look at the ones before it
        a = F.scaled_dot_product_attention(
            q, k, v, is_causal=True, dropout_p=self.dropout if self.training else 0.0
        )
        x = x + self.proj(a.transpose(1, 2).reshape(B, T, C))
        return x + self.mlp(self.ln2(x))


class TinyGPT(nn.Module):
    def __init__(self, vocab_size, block_size=128, n_layer=4, n_head=4, n_embd=128, dropout=0.1):
        super().__init__()
        self.block_size = block_size
        self.tok_emb = nn.Embedding(vocab_size, n_embd)
        self.pos_emb = nn.Embedding(block_size, n_embd)
        self.blocks = nn.ModuleList(Block(n_embd, n_head, dropout) for _ in range(n_layer))
        self.ln_f = nn.LayerNorm(n_embd)
        self.head = nn.Linear(n_embd, vocab_size)

    def forward(self, idx, targets=None):
        T = idx.shape[1]
        x = self.tok_emb(idx) + self.pos_emb(torch.arange(T, device=idx.device))
        for block in self.blocks:
            x = block(x)
        logits = self.head(self.ln_f(x))
        loss = None
        if targets is not None:
            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1))
        return logits, loss

    @torch.no_grad()
    def generate(self, idx, max_new_tokens, temperature=0.8, top_k=None):
        """Yield one new token id at a time, feeding each back in as input."""
        for _ in range(max_new_tokens):
            logits, _ = self(idx[:, -self.block_size:])
            logits = logits[:, -1, :] / max(temperature, 1e-5)
            if top_k:
                kth = torch.topk(logits, min(top_k, logits.size(-1))).values[:, [-1]]
                logits[logits < kth] = -float("inf")
            nxt = torch.multinomial(F.softmax(logits, dim=-1), 1)
            idx = torch.cat([idx, nxt], dim=1)
            yield nxt.item()