Upload model.py with huggingface_hub

model.py

@@ -0,0 +1,163 @@
+"""
+Stage 2: MODEL ARCHITECTURE.
+
+A from-scratch GPT-style decoder-only transformer, built directly in PyTorch
+(no pretrained weights, no transformers.AutoModel -- this is the part that
+makes "built an LLM from scratch" an honest claim):
+  - token + positional embeddings
+  - N transformer blocks, each with: multi-head causal self-attention,
+    a feed-forward MLP, and layer norm (pre-norm, like GPT-2)
+  - a final layer norm + linear head tied to the token embedding weights
+
+Sizes (see PRESETS below):
+  - "tiny"   ~ a few M params  -> for a fast CPU dry-run / sanity check
+  - "small"  ~ 30M params      -> trains in well under an hour on an RTX 3060
+  - "medium" ~ 125M params     -> GPT-1 scale, still fits an RTX 3060 12GB
+"""
+import math
+from dataclasses import dataclass
+
+import torch
+import torch.nn as nn
+from torch.nn import functional as F
+
+PRESETS = {
+    "tiny": dict(n_layer=4, n_head=4, n_embd=128, block_size=128),   # CPU dry-run
+    "small": dict(n_layer=6, n_head=6, n_embd=384, block_size=256),  # ~30M params
+    "medium": dict(n_layer=12, n_head=12, n_embd=768, block_size=512),  # ~125M params
+}
+
+
+@dataclass
+class GPTConfig:
+    vocab_size: int = 8000
+    block_size: int = 256
+    n_layer: int = 6
+    n_head: int = 6
+    n_embd: int = 384
+    dropout: float = 0.1
+
+
+class CausalSelfAttention(nn.Module):
+    def __init__(self, config: GPTConfig):
+        super().__init__()
+        assert config.n_embd % config.n_head == 0
+        self.n_head = config.n_head
+        self.head_dim = config.n_embd // config.n_head
+        self.qkv = nn.Linear(config.n_embd, 3 * config.n_embd)
+        self.proj = nn.Linear(config.n_embd, config.n_embd)
+        self.attn_dropout = nn.Dropout(config.dropout)
+        self.resid_dropout = nn.Dropout(config.dropout)
+        mask = torch.tril(torch.ones(config.block_size, config.block_size))
+        self.register_buffer("mask", mask.view(1, 1, config.block_size, config.block_size))
+
+    def forward(self, x):
+        B, T, C = x.shape
+        qkv = self.qkv(x)
+        q, k, v = qkv.split(C, dim=2)
+        q = q.view(B, T, self.n_head, self.head_dim).transpose(1, 2)
+        k = k.view(B, T, self.n_head, self.head_dim).transpose(1, 2)
+        v = v.view(B, T, self.n_head, self.head_dim).transpose(1, 2)
+
+        att = (q @ k.transpose(-2, -1)) / math.sqrt(self.head_dim)
+        att = att.masked_fill(self.mask[:, :, :T, :T] == 0, float("-inf"))
+        att = F.softmax(att, dim=-1)
+        att = self.attn_dropout(att)
+        y = att @ v
+        y = y.transpose(1, 2).contiguous().view(B, T, C)
+        return self.resid_dropout(self.proj(y))
+
+
+class MLP(nn.Module):
+    def __init__(self, config: GPTConfig):
+        super().__init__()
+        self.fc = nn.Linear(config.n_embd, 4 * config.n_embd)
+        self.proj = nn.Linear(4 * config.n_embd, config.n_embd)
+        self.dropout = nn.Dropout(config.dropout)
+
+    def forward(self, x):
+        return self.dropout(self.proj(F.gelu(self.fc(x))))
+
+
+class Block(nn.Module):
+    def __init__(self, config: GPTConfig):
+        super().__init__()
+        self.ln1 = nn.LayerNorm(config.n_embd)
+        self.attn = CausalSelfAttention(config)
+        self.ln2 = nn.LayerNorm(config.n_embd)
+        self.mlp = MLP(config)
+
+    def forward(self, x):
+        x = x + self.attn(self.ln1(x))
+        x = x + self.mlp(self.ln2(x))
+        return x
+
+
+class GPT(nn.Module):
+    def __init__(self, config: GPTConfig):
+        super().__init__()
+        self.config = config
+        self.tok_emb = nn.Embedding(config.vocab_size, config.n_embd)
+        self.pos_emb = nn.Embedding(config.block_size, config.n_embd)
+        self.drop = nn.Dropout(config.dropout)
+        self.blocks = nn.ModuleList([Block(config) for _ in range(config.n_layer)])
+        self.ln_f = nn.LayerNorm(config.n_embd)
+        self.head = nn.Linear(config.n_embd, config.vocab_size, bias=False)
+        self.head.weight = self.tok_emb.weight  # weight tying
+
+        self.apply(self._init_weights)
+        n_params = sum(p.numel() for p in self.parameters())
+        print(f"GPT initialized: {n_params/1e6:.2f}M parameters "
+              f"(n_layer={config.n_layer}, n_head={config.n_head}, "
+              f"n_embd={config.n_embd}, vocab_size={config.vocab_size}, "
+              f"block_size={config.block_size})")
+
+    def _init_weights(self, module):
+        if isinstance(module, nn.Linear):
+            nn.init.normal_(module.weight, mean=0.0, std=0.02)
+            if module.bias is not None:
+                nn.init.zeros_(module.bias)
+        elif isinstance(module, nn.Embedding):
+            nn.init.normal_(module.weight, mean=0.0, std=0.02)
+
+    def forward(self, idx, targets=None):
+        B, T = idx.shape
+        assert T <= self.config.block_size, "sequence longer than block_size"
+        pos = torch.arange(0, T, device=idx.device).unsqueeze(0)
+        x = self.drop(self.tok_emb(idx) + self.pos_emb(pos))
+        for block in self.blocks:
+            x = block(x)
+        x = self.ln_f(x)
+        logits = self.head(x)
+
+        loss = None
+        if targets is not None:
+            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1), ignore_index=-1)
+        return logits, loss
+
+    @torch.no_grad()
+    def generate(self, idx, max_new_tokens, temperature=1.0, top_k=None, top_p=None):
+        self.eval()
+        for _ in range(max_new_tokens):
+            idx_cond = idx[:, -self.config.block_size:]
+            logits, _ = self(idx_cond)
+            logits = logits[:, -1, :] / max(temperature, 1e-5)
+
+            if top_k is not None:
+                v, _ = torch.topk(logits, min(top_k, logits.size(-1)))
+                logits[logits < v[:, [-1]]] = float("-inf")
+
+            if top_p is not None:
+                sorted_logits, sorted_idx = torch.sort(logits, descending=True)
+                probs = F.softmax(sorted_logits, dim=-1)
+                cum_probs = torch.cumsum(probs, dim=-1)
+                remove = cum_probs > top_p
+                remove[:, 1:] = remove[:, :-1].clone()
+                remove[:, 0] = False
+                sorted_logits[remove] = float("-inf")
+                logits = torch.full_like(logits, float("-inf")).scatter(1, sorted_idx, sorted_logits)
+
+            probs = F.softmax(logits, dim=-1)
+            next_id = torch.multinomial(probs, num_samples=1)
+            idx = torch.cat([idx, next_id], dim=1)
+        return idx