Upload 7 files

block.py

@@ -0,0 +1,21 @@
+import torch.nn as nn
+
+from multi_head_attention import MultiHeadAttention
+from feedforward import FeedFoward
+
+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

data_utils.py

@@ -0,0 +1,49 @@
+import torch
+
+with open('data/input.txt', 'r', encoding='utf-8') as f:
+    text = f.read()
+
+# here are all the unique characters that occur in this text
+chars = sorted(list(set(text)))
+vocab_size = len(chars)
+# create a mapping from characters to integers
+stoi = { ch:i for i,ch in enumerate(chars) }
+itos = { i:ch for i,ch in enumerate(chars) }
+encode = lambda s: [stoi[c] for c in s] # encoder: take a string, output a list of integers
+decode = lambda l: ''.join([itos[i] for i in l]) # decoder: take a list of integers, output a string
+
+# Train and test splits
+data = torch.tensor(encode(text), dtype=torch.long)
+n = int(0.9*len(data)) # first 90% will be train, rest val
+train_data = data[:n]
+val_data = data[n:]
+
+'''
+'''
+def get_train_data():
+    return train_data
+
+'''
+'''
+def get_val_data():
+    return val_data
+
+'''
+'''
+def get_data():
+    return data
+
+'''
+'''
+def get_encoder():
+    return encode
+
+'''
+'''
+def get_decoder():
+    return decode
+
+'''
+'''
+def get_vocab_size():
+    return vocab_size

feedforward.py

@@ -0,0 +1,17 @@
+import torch.nn as nn
+import gpt_config as config
+
+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(config.dropout),
+        )
+
+    def forward(self, x):
+        return self.net(x)

gpt_config.py

@@ -0,0 +1,16 @@
+import torch
+
+# hyperparameters
+batch_size = 64 # how many independent sequences will we process in parallel?
+block_size = 256 # what is the maximum context length for predictions?
+max_iters = 10000
+eval_interval = 500
+learning_rate = 3e-4
+# device = 'cuda' if torch.cuda.is_available() else 'cpu'
+device = 'mps'
+eval_iters = 200
+n_embd = 384
+n_head = 6
+n_layer = 6
+dropout = 0.2
+vocab_size = 65

gpt_language_model.py

@@ -0,0 +1,66 @@
+import torch
+import torch.nn as nn
+from torch.nn import functional as F
+
+import gpt_config as config
+from block import Block
+
+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(config.vocab_size, config.n_embd)
+        self.position_embedding_table = nn.Embedding(config.block_size, config.n_embd)
+        self.blocks = nn.Sequential(*[Block(config.n_embd, n_head=config.n_head) for _ in range(config.n_layer)])
+        self.ln_f = nn.LayerNorm(config.n_embd) # final layer norm
+        self.lm_head = nn.Linear(config.n_embd, config.vocab_size)
+
+        # better init, not covered in the original GPT video, but important, will cover in followup video
+        self.apply(self._init_weights)
+
+    def _init_weights(self, module):
+        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)
+        elif isinstance(module, nn.Embedding):
+            torch.nn.init.normal_(module.weight, mean=0.0, std=0.02)
+
+    def forward(self, idx, targets=None):
+        B, T = idx.shape
+
+        # 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=config.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[:, -config.block_size:]
+            # 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

head.py

@@ -0,0 +1,33 @@
+import torch
+import torch.nn as nn
+from torch.nn import functional as F
+
+import gpt_config as config
+
+class Head(nn.Module):
+    """ one head of self-attention """
+
+    def __init__(self, head_size):
+        super().__init__()
+        self.key = nn.Linear(config.n_embd, head_size, bias=False)
+        self.query = nn.Linear(config.n_embd, head_size, bias=False)
+        self.value = nn.Linear(config.n_embd, head_size, bias=False)
+        self.register_buffer('tril', torch.tril(torch.ones(config.block_size, config.block_size)))
+
+        self.dropout = nn.Dropout(config.dropout)
+
+    def forward(self, x):
+        # input of size (batch, time-step, channels)
+        # output of size (batch, time-step, head size)
+        B,T,C = x.shape
+        k = self.key(x)   # (B,T,hs)
+        q = self.query(x) # (B,T,hs)
+        # compute attention scores ("affinities")
+        wei = q @ k.transpose(-2,-1) * k.shape[-1]**-0.5 # (B, T, hs) @ (B, hs, 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,hs)
+        out = wei @ v # (B, T, T) @ (B, T, hs) -> (B, T, hs)
+        return out

multi_head_attention.py

@@ -0,0 +1,19 @@
+import torch
+import torch.nn as nn
+
+import gpt_config as config
+from head import Head
+
+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(head_size * num_heads, config.n_embd)
+        self.dropout = nn.Dropout(config.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