"""
Parametrisiertes GPT — Modelldefinition für pretrain.py, finetune_chat.py,
chat.py und sample_all.py (v3, eigener BPE-Tokenizer mit 8192 Vokabeln).
"""

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


class Head(nn.Module):
    """ one head of self-attention """

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

    def forward(self, x):
        B, T, C = x.shape
        k = self.key(x)
        q = self.query(x)
        wei = q @ k.transpose(-2, -1) * k.shape[-1] ** -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)
        return wei @ v


class MultiHeadAttention(nn.Module):
    def __init__(self, n_embd, n_head, block_size, dropout):
        super().__init__()
        head_size = n_embd // n_head
        self.heads = nn.ModuleList(
            [Head(n_embd, head_size, block_size, dropout) for _ in range(n_head)])
        self.proj = nn.Linear(n_embd, n_embd)
        self.dropout = nn.Dropout(dropout)

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


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

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


class Block(nn.Module):
    def __init__(self, n_embd, n_head, block_size, dropout):
        super().__init__()
        self.sa = MultiHeadAttention(n_embd, n_head, block_size, dropout)
        self.ffwd = FeedForward(n_embd, dropout)
        self.ln1 = nn.LayerNorm(n_embd)
        self.ln2 = nn.LayerNorm(n_embd)

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


class GPTLanguageModel(nn.Module):

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

        self.apply(self._init_weights)

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

        if targets is None:
            loss = None
        else:
            B, T, C = logits.shape
            loss = F.cross_entropy(logits.view(B * T, C), targets.view(B * T))
        return logits, loss

    @torch.no_grad()
    def generate(self, idx, max_new_tokens, temperature=1.0, top_k=None,
                 stop_tokens=None, repetition_penalty=1.0):
        """Sampelt Tokens; bricht ab, sobald ein stop_token erzeugt wurde
        (das Stop-Token selbst wird nicht angehängt)."""
        stop_tokens = set(stop_tokens or [])
        for _ in range(max_new_tokens):
            idx_cond = idx[:, -self.block_size:]
            logits, _ = self(idx_cond)
            logits = logits[:, -1, :] / max(temperature, 1e-5)
            if repetition_penalty != 1.0:
                recent = idx[0, -64:].tolist()
                for t in set(recent):
                    logits[0, t] /= repetition_penalty
            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)
            if idx_next.item() in stop_tokens:
                break
            idx = torch.cat((idx, idx_next), dim=1)
        return idx


def get_device() -> str:
    if torch.backends.mps.is_available():
        return 'mps'
    if torch.cuda.is_available():
        return 'cuda'
    return 'cpu'


def model_from_checkpoint(ckpt, device):
    cfg = ckpt['config']
    model = GPTLanguageModel(
        vocab_size=ckpt['vocab_size'],
        n_embd=cfg['n_embd'], n_head=cfg['n_head'], n_layer=cfg['n_layer'],
        block_size=cfg['block_size'], dropout=cfg['dropout'])
    model.load_state_dict(ckpt['model_state_dict'])
    return model.to(device)