Add nanogpt examples (#79)

* added nanogpt example
set torch version >= 2.1.0 in pyproject.toml
changed message when there are multiple cupti subscribers

* deleted comments in session.py - habitat section

* removed session.py from PR

---------

Co-authored-by: John Calderon <[email protected]>

Author: johncalesp

examples/nanogpt/entry_point.py

@@ -0,0 +1,85 @@
+import numpy as np
+import torch
+from torch import nn
+
+from model import GPTConfig, GPT
+
+# Batch size.
+block_size = 32
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+# model
+n_layer = 16  
+n_head = 16  
+n_embd = 512  
+dropout = 0.0
+vocab_size = 65
+bias = False
+
+# Adamw optimizer
+learning_rate = 6e-4
+weight_decay = 1e-1
+beta1 = 0.9
+beta2 = 0.95
+
+
+# optimizer
+def configure_optimizer(model, weight_decay, learning_rate, betas):
+    param_dict = {pn: p for pn, p in model.named_parameters()}
+    param_dict = {pn: p for pn, p in param_dict.items() if p.requires_grad}
+    decay_params = [p for n, p in param_dict.items() if p.dim() >= 2]
+    nodecay_params = [p for n, p in param_dict.items() if p.dim() < 2]
+    optim_groups = [
+        {"params": decay_params, "weight_decay": weight_decay},
+        {"params": nodecay_params, "weight_decay": 0.0},
+    ]
+    optimizer = torch.optim.AdamW(optim_groups, lr=learning_rate, betas=betas)
+
+    return optimizer
+
+def deepview_model_provider():
+    # model init
+    # ---------------------------------------------
+    # Enable flash attention
+    enable_flash_attention = False
+    model_args = dict(
+        n_layer=n_layer,
+        n_head=n_head,
+        n_embd=n_embd,
+        block_size=block_size,
+        bias=bias,
+        vocab_size=vocab_size,
+        dropout=dropout,
+        enable_flash_attention=enable_flash_attention,
+    )
+    gptconf = GPTConfig(**model_args)
+    model = GPT(gptconf)
+    return model.to(device)
+
+
+def deepview_input_provider(batch_size=48):
+    data = np.random.randint(vocab_size, size=(batch_size, block_size + 1))
+    x = torch.stack(
+        [torch.from_numpy((data[i, :-1]).astype(np.int64)) for i in range(batch_size)]
+    )
+    y = torch.stack(
+        [torch.from_numpy((data[i, 1:]).astype(np.int64)) for i in range(batch_size)]
+    )
+
+    return (x.to(device), y.to(device))
+
+
+def deepview_iteration_provider(model):
+    criterion = nn.CrossEntropyLoss()
+    optimizer = torch.optim.AdamW(
+        model.parameters(), lr=learning_rate, betas=(beta1, beta2)
+    )
+
+    def iteration(inputs, targets):
+        optimizer.zero_grad()
+        outputs = model(inputs)
+        loss = criterion(outputs.view(-1, outputs.size(-1)), targets.view(-1))
+        loss.backward()
+        optimizer.step()
+
+    return iteration

examples/nanogpt/model.py

@@ -0,0 +1,192 @@
+"""
+Model Reference: https://github.com/karpathy/nanoGPT
+Full definition of a GPT Language Model, all of it in this single file.
+References:
+1) the official GPT-2 TensorFlow implementation released by OpenAI:
+https://github.com/openai/gpt-2/blob/master/src/model.py
+2) huggingface/transformers PyTorch implementation:
+https://github.com/huggingface/transformers/blob/main/src/transformers/models/gpt2/modeling_gpt2.py
+"""
+
+import math
+from dataclasses import dataclass
+
+import torch
+import torch.nn as nn
+from torch.nn import functional as F
+
+# @torch.jit.script # good to enable when not using torch.compile, disable when using (our default)
+def new_gelu(x):
+    """
+    Implementation of the GELU activation function currently in Google BERT repo (identical to OpenAI GPT).
+    Reference: Gaussian Error Linear Units (GELU) paper: https://arxiv.org/abs/1606.08415
+    """
+    return 0.5 * x * (1.0 + torch.tanh(math.sqrt(2.0 / math.pi) * (x + 0.044715 * torch.pow(x, 3.0))))
+
+class LayerNorm(nn.Module):
+    """ LayerNorm but with an optional bias. PyTorch doesn't support simply bias=False """
+
+    def __init__(self, ndim, bias):
+        super().__init__()
+        self.weight = nn.Parameter(torch.ones(ndim))
+        self.bias = nn.Parameter(torch.zeros(ndim)) if bias else None
+
+    def forward(self, input):
+        return F.layer_norm(input, self.weight.shape, self.weight, self.bias, 1e-5) 
+
+class CausalSelfAttention(nn.Module):
+
+    def __init__(self, config):
+        super().__init__()
+        assert config.n_embd % config.n_head == 0
+        # key, query, value projections for all heads, but in a batch
+        self.c_attn = nn.Linear(config.n_embd, 3 * config.n_embd, bias=config.bias)
+        # output projection
+        self.c_proj = nn.Linear(config.n_embd, config.n_embd, bias=config.bias)
+        # regularization
+        self.attn_dropout = nn.Dropout(config.dropout)
+        self.resid_dropout = nn.Dropout(config.dropout)
+        self.n_head = config.n_head
+        self.n_embd = config.n_embd
+        self.dropout = config.dropout
+        # flash attention only in PyTorch >= 2.0
+        self.flash = hasattr(torch.nn.functional, 'scaled_dot_product_attention') if config.enable_flash_attention else False
+        if not self.flash:
+            # print("WARNING: using slow attention. Flash Attention requires PyTorch >= 2.0")
+            # causal mask to ensure that attention is only applied to the left in the input sequence
+            self.register_buffer("bias", torch.tril(torch.ones(config.block_size, config.block_size))
+                                        .view(1, 1, config.block_size, config.block_size))
+
+    def forward(self, x):
+        B, T, C = x.size() # batch size, sequence length, embedding dimensionality (n_embd)
+
+        # calculate query, key, values for all heads in batch and move head forward to be the batch dim
+        q, k, v  = self.c_attn(x).split(self.n_embd, dim=2)
+        k = k.view(B, T, self.n_head, C // self.n_head).transpose(1, 2) # (B, nh, T, hs)
+        q = q.view(B, T, self.n_head, C // self.n_head).transpose(1, 2) # (B, nh, T, hs)
+        v = v.view(B, T, self.n_head, C // self.n_head).transpose(1, 2) # (B, nh, T, hs)
+
+        # causal self-attention; Self-attend: (B, nh, T, hs) x (B, nh, hs, T) -> (B, nh, T, T)
+        if self.flash:
+            # efficient attention using Flash Attention CUDA kernels
+            y = torch.nn.functional.scaled_dot_product_attention(q, k, v, attn_mask=None, dropout_p=self.dropout if self.training else 0, is_causal=True)
+        else:
+            # manual implementation of attention
+            att = (q @ k.transpose(-2, -1)) * (1.0 / math.sqrt(k.size(-1)))
+            att = att.masked_fill(self.bias[:,:,:T,:T] == 0, float('-inf'))
+            att = F.softmax(att, dim=-1)
+            att = self.attn_dropout(att)
+            y = att @ v # (B, nh, T, T) x (B, nh, T, hs) -> (B, nh, T, hs)
+        y = y.transpose(1, 2).contiguous().view(B, T, C) # re-assemble all head outputs side by side
+
+        # output projection
+        y = self.resid_dropout(self.c_proj(y))
+        return y
+
+class MLP(nn.Module):
+
+    def __init__(self, config):
+        super().__init__()
+        self.c_fc    = nn.Linear(config.n_embd, 4 * config.n_embd, bias=config.bias)
+        self.c_proj  = nn.Linear(4 * config.n_embd, config.n_embd, bias=config.bias)
+        self.dropout = nn.Dropout(config.dropout)
+
+    def forward(self, x):
+        x = self.c_fc(x)
+        x = new_gelu(x)
+        x = self.c_proj(x)
+        x = self.dropout(x)
+        return x
+
+class Block(nn.Module):
+
+    def __init__(self, config):
+        super().__init__()
+        self.ln_1 = LayerNorm(config.n_embd, bias=config.bias)
+        self.attn = CausalSelfAttention(config)
+        self.ln_2 = LayerNorm(config.n_embd, bias=config.bias)
+        self.mlp = MLP(config)
+
+    def forward(self, x):
+        x = x + self.attn(self.ln_1(x))
+        x = x + self.mlp(self.ln_2(x))
+        return x
+
+@dataclass
+class GPTConfig:
+    block_size: int = 1024
+    vocab_size: int = 50304 # GPT-2 vocab_size of 50257, padded up to nearest multiple of 64 for efficiency
+    n_layer: int = 12
+    n_head: int = 12
+    n_embd: int = 768
+    dropout: float = 0.0
+    enable_flash_attention: bool = False
+    bias: bool = True # True: bias in Linears and LayerNorms, like GPT-2. False: a bit better and faster
+
+class GPT(nn.Module):
+
+    def __init__(self, config):
+        super().__init__()
+        assert config.vocab_size is not None
+        assert config.block_size is not None
+        self.config = config
+
+        self.transformer = nn.ModuleDict(dict(
+            wte = nn.Embedding(config.vocab_size, config.n_embd),
+            wpe = nn.Embedding(config.block_size, config.n_embd),
+            drop = nn.Dropout(config.dropout),
+            h = nn.ModuleList([Block(config) for _ in range(config.n_layer)]),
+            ln_f = LayerNorm(config.n_embd, bias=config.bias),
+        ))
+        self.lm_head = nn.Linear(config.n_embd, config.vocab_size, bias=False)
+        # with weight tying when using torch.compile() some warnings get generated:
+        # "UserWarning: functional_call was passed multiple values for tied weights.
+        # This behavior is deprecated and will be an error in future versions"
+        # not 100% sure what this is, so far seems to be harmless. TODO investigate
+        self.transformer.wte.weight = self.lm_head.weight # https://paperswithcode.com/method/weight-tying
+
+        # init all weights
+        self.apply(self._init_weights)
+        # apply special scaled init to the residual projections, per GPT-2 paper
+        for pn, p in self.named_parameters():
+            if pn.endswith('c_proj.weight'):
+                torch.nn.init.normal_(p, mean=0.0, std=0.02/math.sqrt(2 * config.n_layer))
+
+        # report number of parameters
+        print("number of parameters: %.2fM" % (self.get_num_params()/1e6,))
+
+    def get_num_params(self, non_embedding=True):
+        """
+        Return the number of parameters in the model.
+        For non-embedding count (default), the position embeddings get subtracted.
+        The token embeddings would too, except due to the parameter sharing these
+        params are actually used as weights in the final layer, so we include them.
+        """
+        n_params = sum(p.numel() for p in self.parameters())
+        if non_embedding:
+            n_params -= self.transformer.wpe.weight.numel()
+        return n_params
+
+    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):
+        device = idx.device
+        b, t = idx.size()
+        assert t <= self.config.block_size, f"Cannot forward sequence of length {t}, block size is only {self.config.block_size}"
+        pos = torch.arange(0, t, dtype=torch.long, device=device).unsqueeze(0) # shape (1, t)
+
+        # forward the GPT model itself
+        tok_emb = self.transformer.wte(idx) # token embeddings of shape (b, t, n_embd)
+        pos_emb = self.transformer.wpe(pos) # position embeddings of shape (1, t, n_embd)
+        x = self.transformer.drop(tok_emb + pos_emb)
+        for block in self.transformer.h:
+            x = block(x)
+        x = self.transformer.ln_f(x)
+        logits = self.lm_head(x)
+        return logits

pyproject.toml

@@ -28,7 +28,7 @@ python = "^3.7"
 pyyaml = "*"
 protobuf = "3.19.6"
 numpy = "^1.15.2"
-torch = ">=1.13.1"
+torch = ">=2.1.0"
 nvidia-ml-py3 = "*"
 toml = "^0.10.2"
 pyRAPL = "^0.2.3"