From 0b176bb1fc47527ea3088e5e54fce70a8ce315ce Mon Sep 17 00:00:00 2001 From: rasbt Date: Tue, 14 May 2024 08:11:58 -0500 Subject: [PATCH] add previous chapters file --- .../previous_chapters.py | 321 ++++++++++++++++++ 1 file changed, 321 insertions(+) create mode 100644 ch06/03_bonus_imdb-classification/previous_chapters.py diff --git a/ch06/03_bonus_imdb-classification/previous_chapters.py b/ch06/03_bonus_imdb-classification/previous_chapters.py new file mode 100644 index 0000000..4fc0f7e --- /dev/null +++ b/ch06/03_bonus_imdb-classification/previous_chapters.py @@ -0,0 +1,321 @@ +# Copyright (c) Sebastian Raschka under Apache License 2.0 (see LICENSE.txt). +# Source for "Build a Large Language Model From Scratch" +# - https://www.manning.com/books/build-a-large-language-model-from-scratch +# Code: https://github.com/rasbt/LLMs-from-scratch +# +# This file collects all the relevant code that we covered thus far +# throughout Chapters 2-5. +# This file can be run as a standalone script. + +import numpy as np +import tiktoken +import torch +import torch.nn as nn +from torch.utils.data import Dataset, DataLoader + +##################################### +# Chapter 2 +##################################### + + +class GPTDatasetV1(Dataset): + def __init__(self, txt, tokenizer, max_length, stride): + self.tokenizer = tokenizer + self.input_ids = [] + self.target_ids = [] + + # Tokenize the entire text + token_ids = tokenizer.encode(txt) + + # Use a sliding window to chunk the book into overlapping sequences of max_length + for i in range(0, len(token_ids) - max_length, stride): + input_chunk = token_ids[i:i + max_length] + target_chunk = token_ids[i + 1: i + max_length + 1] + self.input_ids.append(torch.tensor(input_chunk)) + self.target_ids.append(torch.tensor(target_chunk)) + + def __len__(self): + return len(self.input_ids) + + def __getitem__(self, idx): + return self.input_ids[idx], self.target_ids[idx] + + +def create_dataloader_v1(txt, batch_size=4, max_length=256, + stride=128, shuffle=True, drop_last=True): + # Initialize the tokenizer + tokenizer = tiktoken.get_encoding("gpt2") + + # Create dataset + dataset = GPTDatasetV1(txt, tokenizer, max_length, stride) + + # Create dataloader + dataloader = DataLoader( + dataset, batch_size=batch_size, shuffle=shuffle, drop_last=drop_last) + + return dataloader + + +##################################### +# Chapter 3 +##################################### +class MultiHeadAttention(nn.Module): + def __init__(self, d_in, d_out, context_length, dropout, num_heads, qkv_bias=False): + super().__init__() + assert d_out % num_heads == 0, "d_out must be divisible by n_heads" + + self.d_out = d_out + self.num_heads = num_heads + self.head_dim = d_out // num_heads # Reduce the projection dim to match desired output dim + + self.W_query = nn.Linear(d_in, d_out, bias=qkv_bias) + self.W_key = nn.Linear(d_in, d_out, bias=qkv_bias) + self.W_value = nn.Linear(d_in, d_out, bias=qkv_bias) + self.out_proj = nn.Linear(d_out, d_out) # Linear layer to combine head outputs + self.dropout = nn.Dropout(dropout) + self.register_buffer('mask', torch.triu(torch.ones(context_length, context_length), diagonal=1)) + + def forward(self, x): + b, num_tokens, d_in = x.shape + + keys = self.W_key(x) # Shape: (b, num_tokens, d_out) + queries = self.W_query(x) + values = self.W_value(x) + + # We implicitly split the matrix by adding a `num_heads` dimension + # Unroll last dim: (b, num_tokens, d_out) -> (b, num_tokens, num_heads, head_dim) + keys = keys.view(b, num_tokens, self.num_heads, self.head_dim) + values = values.view(b, num_tokens, self.num_heads, self.head_dim) + queries = queries.view(b, num_tokens, self.num_heads, self.head_dim) + + # Transpose: (b, num_tokens, num_heads, head_dim) -> (b, num_heads, num_tokens, head_dim) + keys = keys.transpose(1, 2) + queries = queries.transpose(1, 2) + values = values.transpose(1, 2) + + # Compute scaled dot-product attention (aka self-attention) with a causal mask + attn_scores = queries @ keys.transpose(2, 3) # Dot product for each head + + # Original mask truncated to the number of tokens and converted to boolean + mask_bool = self.mask.bool()[:num_tokens, :num_tokens] + + # Use the mask to fill attention scores + attn_scores.masked_fill_(mask_bool, -torch.inf) + + attn_weights = torch.softmax(attn_scores / keys.shape[-1]**0.5, dim=-1) + attn_weights = self.dropout(attn_weights) + + # Shape: (b, num_tokens, num_heads, head_dim) + context_vec = (attn_weights @ values).transpose(1, 2) + + # Combine heads, where self.d_out = self.num_heads * self.head_dim + context_vec = context_vec.reshape(b, num_tokens, self.d_out) + context_vec = self.out_proj(context_vec) # optional projection + + return context_vec + + +##################################### +# Chapter 4 +##################################### +class LayerNorm(nn.Module): + def __init__(self, emb_dim): + super().__init__() + self.eps = 1e-5 + self.scale = nn.Parameter(torch.ones(emb_dim)) + self.shift = nn.Parameter(torch.zeros(emb_dim)) + + def forward(self, x): + mean = x.mean(dim=-1, keepdim=True) + var = x.var(dim=-1, keepdim=True, unbiased=False) + norm_x = (x - mean) / torch.sqrt(var + self.eps) + return self.scale * norm_x + self.shift + + +class GELU(nn.Module): + def __init__(self): + super().__init__() + + def forward(self, x): + return 0.5 * x * (1 + torch.tanh( + torch.sqrt(torch.tensor(2.0 / torch.pi)) * + (x + 0.044715 * torch.pow(x, 3)) + )) + + +class FeedForward(nn.Module): + def __init__(self, cfg): + super().__init__() + self.layers = nn.Sequential( + nn.Linear(cfg["emb_dim"], 4 * cfg["emb_dim"]), + GELU(), + nn.Linear(4 * cfg["emb_dim"], cfg["emb_dim"]), + ) + + def forward(self, x): + return self.layers(x) + + +class TransformerBlock(nn.Module): + def __init__(self, cfg): + super().__init__() + self.att = MultiHeadAttention( + d_in=cfg["emb_dim"], + d_out=cfg["emb_dim"], + context_length=cfg["context_length"], + num_heads=cfg["n_heads"], + dropout=cfg["drop_rate"], + qkv_bias=cfg["qkv_bias"]) + self.ff = FeedForward(cfg) + self.norm1 = LayerNorm(cfg["emb_dim"]) + self.norm2 = LayerNorm(cfg["emb_dim"]) + self.drop_resid = nn.Dropout(cfg["drop_rate"]) + + def forward(self, x): + # Shortcut connection for attention block + shortcut = x + x = self.norm1(x) + x = self.att(x) # Shape [batch_size, num_tokens, emb_size] + x = self.drop_resid(x) + x = x + shortcut # Add the original input back + + # Shortcut connection for feed-forward block + shortcut = x + x = self.norm2(x) + x = self.ff(x) + x = self.drop_resid(x) + x = x + shortcut # Add the original input back + + return x + + +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"]) + + self.trf_blocks = nn.Sequential( + *[TransformerBlock(cfg) for _ in range(cfg["n_layers"])]) + + 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 # Shape [batch_size, num_tokens, emb_size] + x = self.drop_emb(x) + x = self.trf_blocks(x) + x = self.final_norm(x) + logits = self.out_head(x) + return logits + + +def generate_text_simple(model, idx, max_new_tokens, context_size): + # idx is (B, T) 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_token, vocab_size) becomes (batch, vocab_size) + logits = logits[:, -1, :] + + # Get the idx of the vocab entry with the highest logits value + idx_next = torch.argmax(logits, 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 + + +##################################### +# Chapter 5 +##################################### +def assign(left, right): + if left.shape != right.shape: + raise ValueError(f"Shape mismatch. Left: {left.shape}, Right: {right.shape}") + return torch.nn.Parameter(torch.tensor(right)) + + +def load_weights_into_gpt(gpt, params): + gpt.pos_emb.weight = assign(gpt.pos_emb.weight, params['wpe']) + gpt.tok_emb.weight = assign(gpt.tok_emb.weight, params['wte']) + + for b in range(len(params["blocks"])): + q_w, k_w, v_w = np.split( + (params["blocks"][b]["attn"]["c_attn"])["w"], 3, axis=-1) + gpt.trf_blocks[b].att.W_query.weight = assign( + gpt.trf_blocks[b].att.W_query.weight, q_w.T) + gpt.trf_blocks[b].att.W_key.weight = assign( + gpt.trf_blocks[b].att.W_key.weight, k_w.T) + gpt.trf_blocks[b].att.W_value.weight = assign( + gpt.trf_blocks[b].att.W_value.weight, v_w.T) + + q_b, k_b, v_b = np.split( + (params["blocks"][b]["attn"]["c_attn"])["b"], 3, axis=-1) + gpt.trf_blocks[b].att.W_query.bias = assign( + gpt.trf_blocks[b].att.W_query.bias, q_b) + gpt.trf_blocks[b].att.W_key.bias = assign( + gpt.trf_blocks[b].att.W_key.bias, k_b) + gpt.trf_blocks[b].att.W_value.bias = assign( + gpt.trf_blocks[b].att.W_value.bias, v_b) + + gpt.trf_blocks[b].att.out_proj.weight = assign( + gpt.trf_blocks[b].att.out_proj.weight, + params["blocks"][b]["attn"]["c_proj"]["w"].T) + gpt.trf_blocks[b].att.out_proj.bias = assign( + gpt.trf_blocks[b].att.out_proj.bias, + params["blocks"][b]["attn"]["c_proj"]["b"]) + + gpt.trf_blocks[b].ff.layers[0].weight = assign( + gpt.trf_blocks[b].ff.layers[0].weight, + params["blocks"][b]["mlp"]["c_fc"]["w"].T) + gpt.trf_blocks[b].ff.layers[0].bias = assign( + gpt.trf_blocks[b].ff.layers[0].bias, + params["blocks"][b]["mlp"]["c_fc"]["b"]) + gpt.trf_blocks[b].ff.layers[2].weight = assign( + gpt.trf_blocks[b].ff.layers[2].weight, + params["blocks"][b]["mlp"]["c_proj"]["w"].T) + gpt.trf_blocks[b].ff.layers[2].bias = assign( + gpt.trf_blocks[b].ff.layers[2].bias, + params["blocks"][b]["mlp"]["c_proj"]["b"]) + + gpt.trf_blocks[b].norm1.scale = assign( + gpt.trf_blocks[b].norm1.scale, + params["blocks"][b]["ln_1"]["g"]) + gpt.trf_blocks[b].norm1.shift = assign( + gpt.trf_blocks[b].norm1.shift, + params["blocks"][b]["ln_1"]["b"]) + gpt.trf_blocks[b].norm2.scale = assign( + gpt.trf_blocks[b].norm2.scale, + params["blocks"][b]["ln_2"]["g"]) + gpt.trf_blocks[b].norm2.shift = assign( + gpt.trf_blocks[b].norm2.shift, + params["blocks"][b]["ln_2"]["b"]) + + gpt.final_norm.scale = assign(gpt.final_norm.scale, params["g"]) + gpt.final_norm.shift = assign(gpt.final_norm.shift, params["b"]) + gpt.out_head.weight = assign(gpt.out_head.weight, params["wte"]) + + +def text_to_token_ids(text, tokenizer): + encoded = tokenizer.encode(text, allowed_special={'<|endoftext|>'}) + encoded_tensor = torch.tensor(encoded).unsqueeze(0) # add batch dimension + return encoded_tensor + + +def token_ids_to_text(token_ids, tokenizer): + flat = token_ids.squeeze(0) # remove batch dimension + return tokenizer.decode(flat.tolist())