预训练小型GPT (124M参数)

Q = input @ W_q    (768 -> 768)
K = input @ W_k    (768 -> 768)
V = input @ W_v    (768 -> 768)

attention_scores = Q @ K^T / sqrt(d_k)
attention_scores = mask(attention_scores)   # causal mask: -inf for future positions
attention_weights = softmax(attention_scores)
output = attention_weights @ V

import numpy as np

class Embedding:
    def __init__(self, vocab_size, embed_dim, max_seq_len):
        self.token_embed = np.random.randn(vocab_size, embed_dim) * 0.02
        self.pos_embed = np.random.randn(max_seq_len, embed_dim) * 0.02

    def forward(self, token_ids):
        seq_len = token_ids.shape[-1]
        tok_emb = self.token_embed[token_ids]
        pos_emb = self.pos_embed[:seq_len]
        return tok_emb + pos_emb

def attention(Q, K, V, mask=None):
    d_k = Q.shape[-1]
    scores = Q @ K.transpose(0, -1, -2 if Q.ndim == 4 else 1) / np.sqrt(d_k)
    if mask is not None:
        scores = scores + mask
    weights = np.exp(scores - scores.max(axis=-1, keepdims=True))
    weights = weights / weights.sum(axis=-1, keepdims=True)
    return weights @ V

class MultiHeadAttention:
    def __init__(self, embed_dim, num_heads):
        self.num_heads = num_heads
        self.head_dim = embed_dim // num_heads
        self.W_q = np.random.randn(embed_dim, embed_dim) * 0.02
        self.W_k = np.random.randn(embed_dim, embed_dim) * 0.02
        self.W_v = np.random.randn(embed_dim, embed_dim) * 0.02
        self.W_out = np.random.randn(embed_dim, embed_dim) * 0.02

    def forward(self, x, mask=None):
        batch, seq_len, d = x.shape
        Q = (x @ self.W_q).reshape(batch, seq_len, self.num_heads, self.head_dim).transpose(0, 2, 1, 3)
        K = (x @ self.W_k).reshape(batch, seq_len, self.num_heads, self.head_dim).transpose(0, 2, 1, 3)
        V = (x @ self.W_v).reshape(batch, seq_len, self.num_heads, self.head_dim).transpose(0, 2, 1, 3)

        scores = Q @ K.transpose(0, 1, 3, 2) / np.sqrt(self.head_dim)
        if mask is not None:
            scores = scores + mask
        weights = np.exp(scores - scores.max(axis=-1, keepdims=True))
        weights = weights / weights.sum(axis=-1, keepdims=True)
        attn_out = weights @ V

        attn_out = attn_out.transpose(0, 2, 1, 3).reshape(batch, seq_len, d)
        return attn_out @ self.W_out

class LayerNorm:
    def __init__(self, dim, eps=1e-5):
        self.gamma = np.ones(dim)
        self.beta = np.zeros(dim)
        self.eps = eps

    def forward(self, x):
        mean = x.mean(axis=-1, keepdims=True)
        var = x.var(axis=-1, keepdims=True)
        return self.gamma * (x - mean) / np.sqrt(var + self.eps) + self.beta


class FeedForward:
    def __init__(self, embed_dim, ff_dim):
        self.W1 = np.random.randn(embed_dim, ff_dim) * 0.02
        self.b1 = np.zeros(ff_dim)
        self.W2 = np.random.randn(ff_dim, embed_dim) * 0.02
        self.b2 = np.zeros(embed_dim)

    def forward(self, x):
        h = x @ self.W1 + self.b1
        h = np.maximum(0, h)  # GELU approximation: ReLU for simplicity
        return h @ self.W2 + self.b2


class TransformerBlock:
    def __init__(self, embed_dim, num_heads, ff_dim):
        self.ln1 = LayerNorm(embed_dim)
        self.attn = MultiHeadAttention(embed_dim, num_heads)
        self.ln2 = LayerNorm(embed_dim)
        self.ffn = FeedForward(embed_dim, ff_dim)

    def forward(self, x, mask=None):
        x = x + self.attn.forward(self.ln1.forward(x), mask)
        x = x + self.ffn.forward(self.ln2.forward(x))
        return x

class MiniGPT:
    def __init__(self, vocab_size=50257, embed_dim=768, num_heads=12,
                 num_layers=12, max_seq_len=1024, ff_dim=3072):
        self.embedding = Embedding(vocab_size, embed_dim, max_seq_len)
        self.blocks = [
            TransformerBlock(embed_dim, num_heads, ff_dim)
            for _ in range(num_layers)
        ]
        self.ln_f = LayerNorm(embed_dim)
        self.vocab_size = vocab_size
        self.embed_dim = embed_dim

    def forward(self, token_ids):
        seq_len = token_ids.shape[-1]
        mask = np.triu(np.full((seq_len, seq_len), -1e9), k=1)

        x = self.embedding.forward(token_ids)
        for block in self.blocks:
            x = block.forward(x, mask)
        x = self.ln_f.forward(x)

        logits = x @ self.embedding.token_embed.T
        return logits

    def count_parameters(self):
        total = 0
        total += self.embedding.token_embed.size
        total += self.embedding.pos_embed.size
        for block in self.blocks:
            total += block.attn.W_q.size + block.attn.W_k.size
            total += block.attn.W_v.size + block.attn.W_out.size
            total += block.ffn.W1.size + block.ffn.b1.size
            total += block.ffn.W2.size + block.ffn.b2.size
            total += block.ln1.gamma.size + block.ln1.beta.size
            total += block.ln2.gamma.size + block.ln2.beta.size
        total += self.ln_f.gamma.size + self.ln_f.beta.size
        return total

def cross_entropy_loss(logits, targets):
    batch, seq_len, vocab_size = logits.shape
    logits_flat = logits.reshape(-1, vocab_size)
    targets_flat = targets.reshape(-1)

    max_logits = logits_flat.max(axis=-1, keepdims=True)
    log_softmax = logits_flat - max_logits - np.log(
        np.exp(logits_flat - max_logits).sum(axis=-1, keepdims=True)
    )

    loss = -log_softmax[np.arange(len(targets_flat)), targets_flat].mean()
    return loss


def train_mini_gpt(text, vocab_size=256, embed_dim=128, num_heads=4,
                   num_layers=4, seq_len=64, num_steps=200, lr=3e-4):
    tokens = np.array(list(text.encode("utf-8")[:2048]))
    model = MiniGPT(
        vocab_size=vocab_size, embed_dim=embed_dim, num_heads=num_heads,
        num_layers=num_layers, max_seq_len=seq_len, ff_dim=embed_dim * 4
    )

    print(f"Model parameters: {model.count_parameters():,}")
    print(f"Training tokens: {len(tokens):,}")
    print(f"Config: {num_layers} layers, {num_heads} heads, {embed_dim} dims")
    print()

    for step in range(num_steps):
        start_idx = np.random.randint(0, max(1, len(tokens) - seq_len - 1))
        batch_tokens = tokens[start_idx:start_idx + seq_len + 1]

        input_ids = batch_tokens[:-1].reshape(1, -1)
        target_ids = batch_tokens[1:].reshape(1, -1)

        logits = model.forward(input_ids)
        loss = cross_entropy_loss(logits, target_ids)

        if step % 20 == 0:
            print(f"Step {step:4d} | Loss: {loss:.4f}")

    return model

def generate(model, prompt_tokens, max_new_tokens=100, temperature=0.8):
    tokens = list(prompt_tokens)
    seq_len = model.embedding.pos_embed.shape[0]

    for _ in range(max_new_tokens):
        context = np.array(tokens[-seq_len:]).reshape(1, -1)
        logits = model.forward(context)
        next_logits = logits[0, -1, :]

        next_logits = next_logits / temperature
        probs = np.exp(next_logits - next_logits.max())
        probs = probs / probs.sum()

        next_token = np.random.choice(len(probs), p=probs)
        tokens.append(next_token)

    return tokens

corpus = """The transformer architecture has revolutionized natural language processing.
Attention mechanisms allow the model to focus on relevant parts of the input.
Self-attention computes relationships between all pairs of positions in a sequence.
Multi-head attention splits the representation into multiple subspaces.
Each attention head can learn different types of relationships.
The feedforward network provides nonlinear transformations at each position.
Residual connections enable gradient flow through deep networks.
Layer normalization stabilizes training by normalizing activations.
Position embeddings give the model information about token ordering.
The causal mask ensures autoregressive generation during training.
Pre-training on large text corpora teaches the model general language understanding.
Fine-tuning adapts the pre-trained model to specific downstream tasks."""

model = train_mini_gpt(corpus, num_steps=200)

prompt = list("The transformer".encode("utf-8"))
output_tokens = generate(model, prompt, max_new_tokens=100, temperature=0.8)
generated_text = bytes(output_tokens).decode("utf-8", errors="replace")
print(f"\nGenerated: {generated_text}")