从0开始训练自己的LLM（3）

GPT_CONFIG_124M = {
    "vocab_size": 50257,    # Vocabulary size
    "context_length": 1024, # Context length
    "emb_dim": 768,         # Embedding dimension
    "n_heads": 12,          # Number of attention heads
    "n_layers": 12,         # Number of layers
    "drop_rate": 0.1,       # Dropout rate
    "qkv_bias": False       # Query-Key-Value bias
}

import torch
import torch.nn as nn

class GPTModel(nn.Module):
    def __init__(self, cfg):
        super().__init__()
        self.tok_emb = nn.Embedding(cfg["vocab_size"], cfg["emb_dim"])
        self.pos_emb = nn.Embedding(cfg["context_length"], cfg["emb_dim"])
        self.drop_emb = nn.Dropout(cfg["drop_rate"])

        # Use a placeholder for TransformerBlock
        self.trf_blocks = nn.Sequential(
            *[TransformerBlock(cfg) for _ in range(cfg["n_layers"])])

        # Use a placeholder for LayerNorm
        self.final_norm = LayerNorm(cfg["emb_dim"])
        self.out_head = nn.Linear(
            cfg["emb_dim"], cfg["vocab_size"], bias=False
        )

    def forward(self, in_idx):
        batch_size, seq_len = in_idx.shape
        tok_embeds = self.tok_emb(in_idx)
        pos_embeds = self.pos_emb(torch.arange(seq_len, device=in_idx.device))
        x = tok_embeds + pos_embeds
        x = self.drop_emb(x)
        x = self.trf_blocks(x)
        x = self.final_norm(x)
        logits = self.out_head(x)
        return logits


class TransformerBlock(nn.Module):
    def __init__(self, cfg):
        super().__init__()
        # A simple placeholder

    def forward(self, x):
        # This block does nothing and just returns its input.
        return x


class LayerNorm(nn.Module):
    def __init__(self, normalized_shape, eps=1e-5):
        super().__init__()
        # The parameters here are just to mimic the LayerNorm interface.

    def forward(self, x):
        # This layer does nothing and just returns its input.
        return x

def generate_text_simple(model, idx, max_new_tokens, context_size):
    # idx is (batch, n_tokens) array of indices in the current context
    for _ in range(max_new_tokens):

        # Crop current context if it exceeds the supported context size
        # E.g., if LLM supports only 5 tokens, and the context size is 10
        # then only the last 5 tokens are used as context
        idx_cond = idx[:, -context_size:]

        # Get the predictions
        with torch.no_grad():
            logits = model(idx_cond)

        # Focus only on the last time step
        # (batch, n_tokens, vocab_size) becomes (batch, vocab_size)
        logits = logits[:, -1, :]  

        # Apply softmax to get probabilities
        probas = torch.softmax(logits, dim=-1)  # (batch, vocab_size)

        # Get the idx of the vocab entry with the highest probability value
        idx_next = torch.argmax(probas, dim=-1, keepdim=True)  # (batch, 1)

        # Append sampled index to the running sequence
        idx = torch.cat((idx, idx_next), dim=1)  # (batch, n_tokens+1)

    return idx

import tiktoken
tokenizer = tiktoken.get_encoding("gpt2")

start_context = "Hello, I am"

encoded = tokenizer.encode(start_context)
print("encoded:", encoded)

encoded_tensor = torch.tensor(encoded).unsqueeze(0)
print("encoded_tensor.shape:", encoded_tensor.shape)

model.eval() # disable dropout

out = generate_text_simple(
    model=model,
    idx=encoded_tensor, 
    max_new_tokens=6, 
    context_size=GPT_CONFIG_124M["context_length"]
)

print("Output:", out)
print("Output length:", len(out[0]))

decoded_text = tokenizer.decode(out.squeeze(0).tolist())
print(decoded_text)

encoded: [15496, 11, 314, 716] 

encoded_tensor.shape: torch.Size([1, 4]) 

Output: tensor([[15496,    11,   314,   716, 27018, 24086, 47843, 30961, 42348,  7267]]) 

Output length: 10 

Hello, I am Featureiman Byeswickattribute argue