Upload model.py

model.py

@@ -0,0 +1,136 @@
+import torch
+import torch.nn as nn
+from torch.nn import functional as F
+
+class Head(nn.Module):
+    def __init__(self, head_size, n_embd, block_size, dropout):
+        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)
+        q = self.query(x)
+
+        wei = q @ k.transpose(-2, -1) * k.size(-1)**-0.5
+        wei = wei.masked_fill(self.tril[:T, :T] == 0, float('-inf'))
+        wei = F.softmax(wei, dim=-1)
+        wei = self.dropout(wei)
+
+        v = self.value(x)
+        out = wei @ v
+        return out
+
+class MultiHeadAttention(nn.Module):
+    def __init__(self, num_heads, head_size, n_embd, dropout, block_size):
+        super().__init__()
+        self.heads = nn.ModuleList([Head(head_size, n_embd, block_size, dropout) for _ in range(num_heads)])
+        self.proj = nn.Linear(head_size * num_heads, 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.proj(out)
+        return out
+
+class FeedForward(nn.Module):
+    def __init__(self, n_embd, dropout):
+        super().__init__()
+        hidden_dim = 4 * n_embd
+        self.net = nn.Sequential(
+            nn.Linear(n_embd, hidden_dim, bias=False),
+            nn.SiLU(),
+            nn.Linear(hidden_dim, n_embd, bias=False),
+            nn.Dropout(dropout),
+        )
+
+    def forward(self, x):
+        return self.net(x)
+
+class RMSNorm(nn.Module):
+    def __init__(self, dim: int, eps: float = 1e-6):
+        super().__init__()
+        self.eps = eps
+        self.weight = nn.Parameter(torch.ones(dim))
+
+    def _norm(self, x):
+        return x * torch.rsqrt(x.pow(2).mean(-1, keepdim=True) + self.eps)
+
+    def forward(self, x):
+        output = self._norm(x.float()).type_as(x)
+        return output * self.weight
+
+class Block(nn.Module):
+    def __init__(self, n_embd, n_head, dropout, block_size):
+        super().__init__()
+        head_size = n_embd // n_head
+        self.sa = MultiHeadAttention(n_head, head_size, n_embd, dropout, block_size)
+        self.ffwd = FeedForward(n_embd, dropout)
+        self.RMSN1 = RMSNorm(n_embd)
+        self.RMSN2 = RMSNorm(n_embd)
+
+    def forward(self, x):
+        x = x + self.sa(self.RMSN1(x))
+        x = x + self.ffwd(self.RMSN2(x))
+        return x
+
+class TransformerDecoder(nn.Module):
+    def __init__(self, vocab_size, n_embd, block_size, n_head, n_layer, dropout):
+        super().__init__()
+        self.block_size = block_size
+        self.token_embedding_table = nn.Embedding(vocab_size, n_embd)
+        self.position_embeddings_table = nn.Embedding(block_size, n_embd)
+        self.blocks = nn.Sequential(*[Block(n_embd, n_head=n_head, dropout=dropout, block_size=block_size) for _ in range(n_layer)])
+        self.RMSN_f = RMSNorm(n_embd)
+        self.lm_head = nn.Linear(n_embd, vocab_size)
+
+    def forward(self, idx, targets=None):
+        B, T = idx.shape
+        tok_emb = self.token_embedding_table(idx)
+        pos_emb = self.position_embeddings_table(torch.arange(T, device=idx.device))
+        x = tok_emb + pos_emb
+        x = self.blocks(x)
+        x = self.RMSN_f(x)
+        logits = self.lm_head(x)
+
+        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, temperature=1.0, top_k=None, repetition_penalty=1.2):
+        for _ in range(max_new_tokens):
+            idx_cond = idx if idx.size(1) <= self.block_size else idx[:, -self.block_size:]
+            logits, _ = self(idx_cond)
+            logits = logits[:, -1, :]
+
+            if repetition_penalty != 1.0:
+                for i in range(idx_cond.shape[0]):
+                    for token_id in set(idx_cond[i].tolist()):
+                        if logits[i, token_id] > 0:
+                            logits[i, token_id] /= repetition_penalty
+                        else:
+                            logits[i, token_id] *= repetition_penalty
+
+            if temperature != 1.0:
+                logits = logits / temperature
+
+            if top_k is not None:
+                v, _ = torch.topk(logits, min(top_k, logits.size(-1)))
+                logits[logits < v[:, [-1]]] = -float('Inf')
+
+            probs = F.softmax(logits, dim=-1)
+            idx_next = torch.multinomial(probs, num_samples=1)
+
+            idx = torch.cat((idx, idx_next), dim=1)
+
+        return idx