test_model.py

import torch
import torch.nn as nn
from dataclasses import dataclass
from typing import List, Tuple
import torch.nn.functional as F

# NOTE: We take the GPT2 implementation from nanoGPT: https://github.com/karpathy/nanoGPT


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
        self.dropout = config.dropout

    def forward(self, x):
        (B, T, C) = x.size()
        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)
        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)
        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,
        )
        y = y.transpose(1, 2).contiguous().view(B, T, C)
        y = self.resid_dropout(self.c_proj(y))
        return y


class GPTMLP(nn.Module):  # renamed to avoid name conflict
    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 = 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 = GPTMLP(config)
        for module in self.modules():
            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)

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


@dataclass
class GPTConfig:
    block_size: int = 1024
    vocab_size: int = 50304
    n_layer: int = 12
    n_head: int = 12
    n_embd: int = 768
    dropout: float = 0.0
    bias: bool = True
    checkpoint_activations: bool = False


class GPT(nn.Module):
    def __init__(self, config: GPTConfig):
        super().__init__()
        assert config.vocab_size is not None
        assert config.block_size is not None
        self.config = config

        wte = nn.Embedding(config.vocab_size, config.n_embd)
        wpe = nn.Embedding(config.block_size, config.n_embd)
        torch.nn.init.normal_(wte.weight, mean=0.0, std=0.02)
        torch.nn.init.normal_(wpe.weight, mean=0.0, std=0.02)
        blocks: List[Block] = []
        for _ in range(config.n_layer):
            block = Block(config)
            blocks.append(block)
        self.transformer = nn.ModuleDict(
            dict(
                wte=wte,
                wpe=wpe,
                drop=nn.Dropout(config.dropout),
                h=nn.ModuleList(blocks),
                ln_f=nn.LayerNorm(config.n_embd, bias=config.bias),
            )
        )
        self.lm_head = nn.Linear(config.n_embd, config.vocab_size, bias=False)
        self.lm_head.weight = self.transformer.wte.weight

    def forward(
        self, idx: torch.Tensor,
    ) -> Tuple[torch.Tensor, torch.Tensor]:
        device = idx.device
        b, t = idx.size()
        assert (
            t <= self.config.block_size
        ), f"Supports at most {self.config.block_size} but got {t}"
        pos = torch.arange(0, t, dtype=torch.long, device=device)
        tok_emb = self.transformer.wte(idx)
        pos_emb = self.transformer.wpe(pos)
        x = self.transformer.drop(tok_emb + pos_emb)
        for block in self.transformer.h:
            if self.config.checkpoint_activations:
                # We only support composition with non-reentrant AC
                x = torch.utils.checkpoint.checkpoint(
                    block, x, use_reentrant=False
                )
            else:
                x = block(x)
        x = self.transformer.ln_f(x)
        logits = self.lm_head(x)
        return logits
    
def loss_fn(logits: torch.Tensor, targets: torch.Tensor):
    loss = F.cross_entropy(
        logits.view(-1, logits.size(-1)), targets.view(-1), ignore_index=-1
    )
    return loss