Create utils.py

utils.py

@@ -0,0 +1,154 @@
+import torch
+from torch import nn
+import lightning.pytorch as pl
+from torchvision import datasets
+from torch.nn import functional as F
+from torch.utils.data import DataLoader, Dataset, random_splitim
+
+class Head(nn.Module):
+    """ one head of self-attention """
+
+    def __init__(self, head_size):
+        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)   # (B,T,C)
+        q = self.query(x) # (B,T,C)
+        # compute attention scores ("affinities")
+        wei = q @ k.transpose(-2,-1) * C**-0.5 # (B, T, C) @ (B, C, T) -> (B, T, T)
+        wei = wei.masked_fill(self.tril[:T, :T] == 0, float('-inf')) # (B, T, T)
+        wei = F.softmax(wei, dim=-1) # (B, T, T)
+        wei = self.dropout(wei)
+        # perform the weighted aggregation of the values
+        v = self.value(x) # (B,T,C)
+        out = wei @ v # (B, T, T) @ (B, T, C) -> (B, T, C)
+        return out
+
+class MultiHeadAttention(nn.Module):
+    """ multiple heads of self-attention in parallel """
+
+    def __init__(self, num_heads, head_size):
+        super().__init__()
+        self.heads = nn.ModuleList([Head(head_size) for _ in range(num_heads)])
+        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)
+        out = self.dropout(self.proj(out))
+        return out
+
+class FeedFoward(nn.Module):
+    """ a simple linear layer followed by a non-linearity """
+
+    def __init__(self, n_embd):
+        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):
+    """ Transformer block: communication followed by computation """
+
+    def __init__(self, n_embd, n_head):
+        # n_embd: embedding dimension, n_head: the number of heads we'd like
+        super().__init__()
+        head_size = n_embd // n_head
+        self.sa = MultiHeadAttention(n_head, head_size)
+        self.ffwd = FeedFoward(n_embd)
+        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):
+        super().__init__()
+        # each token directly reads off the logits for the next token from a lookup table
+        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=n_head) for _ in range(n_layer)])
+        self.ln_f = nn.LayerNorm(n_embd) # final layer norm
+        self.lm_head = nn.Linear(n_embd, vocab_size)
+
+    def forward(self, idx, targets=None):
+        B, T = idx.shape
+        #print(idx.device)
+        # idx and targets are both (B,T) tensor of integers
+        tok_emb = self.token_embedding_table(idx) # (B,T,C)
+        pos_emb = self.position_embedding_table(torch.arange(T, device=device)) # (T,C)
+        x = tok_emb + pos_emb # (B,T,C)
+        x = self.blocks(x) # (B,T,C)
+        x = self.ln_f(x) # (B,T,C)
+        logits = self.lm_head(x) # (B,T,vocab_size)
+
+        if targets is None:
+            loss = None
+        else:
+            B, T, C = logits.shape
+            logits = logits.view(B*T, C)
+            targets = targets.view(B*T)
+            loss = F.cross_entropy(logits, targets)
+
+        return logits, loss
+
+    def generate(self, idx, max_new_tokens):
+        # idx is (B, T) array of indices in the current context
+        for _ in range(max_new_tokens):
+            # crop idx to the last block_size tokens
+            idx_cond = idx[:, -block_size:].to(device)
+            # get the predictions
+            logits, loss = self(idx_cond)
+            # focus only on the last time step
+            logits = logits[:, -1, :] # becomes (B, C)
+            # apply softmax to get probabilities
+            probs = F.softmax(logits, dim=-1) # (B, C)
+            # sample from the distribution
+            idx_next = torch.multinomial(probs, num_samples=1) # (B, 1)
+            # append sampled index to the running sequence
+            idx = torch.cat((idx, idx_next), dim=1) # (B, T+1)
+        return idx
+
+class GPTLM(pl.LightningModule):
+    def __init__(self):
+      super().__init__()
+      self.model = GPTLanguageModel()
+
+    def forward(self, idx, targets=None):
+      return self.model(idx, targets)
+
+    def process_step(self, batch):
+      xb, yb = batch
+      logits, loss = self(xb, yb)
+      return(logits, loss)
+
+    def training_step(self, batch, batch_idx):
+      _, loss = self.process_step(batch)
+      self.log('train_loss', loss, on_step=True, on_epoch=True, prog_bar=True, logger=True)
+      return loss
+
+    def validation_step(self, batch, batch_idx):
+      _, loss = self.process_step(batch)
+      self.log('val_loss', loss, on_epoch=True, prog_bar=True, logger=True)
+      return loss
+
+    def configure_optimizers(self):
+      optimizer = torch.optim.AdamW(self.parameters(), lr=learning_rate)
+      return optimizer