Upload 2 files

model.py

@@ -0,0 +1,409 @@
+"""
+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
+import inspect
+from dataclasses import dataclass
+
+import torch
+import torch.nn as nn
+from torch.nn import functional as F
+
+# https://github.com/suito555/bitnet158b
+class BitLinear158b(nn.Linear):
+    def __init__(self, in_features, out_features, bias=False, bit_scale = 8):
+        super(BitLinear158b, self).__init__(in_features, out_features, bias)
+        self.bit_scale = bit_scale
+        self.Q_b = 2 ** (self.bit_scale - 1)
+        self.eps = 1e-8
+        
+    def quantize_activations(self, input_norm, abs_max_x_value):
+        scaled_x = input_norm * self.Q_b / (abs_max_x_value + self.eps)
+        quantized_x = torch.round(torch.clamp(
+            scaled_x, -self.Q_b + self.eps, self.Q_b - self.eps
+        ))
+        # Inserting following comment outed line prevents the loss to be NaN if you use torch.compile with torch==2.0.0 or torch==2.2.1
+        # If you use torch==2.1.2, it will not be compiled.
+        if(torch.isnan(scaled_x).any()): 
+            print("Nan!")
+        #STE
+        quantized_x = (quantized_x - scaled_x).detach() + scaled_x
+        return quantized_x
+    
+    def ternarize_weights(self,abs_mean_W_value):
+        scaled_W = self.weight / (abs_mean_W_value + self.eps)
+        quantize_weights = torch.clamp(scaled_W.round(), -1, 1)
+        #STE 
+        quantize_weights = (quantize_weights - self.weight).detach() + self.weight
+        return quantize_weights
+
+    def forward(self, input):
+        input_norm = F.layer_norm(input, (self.in_features,))
+        
+        abs_max_x_value = input_norm.abs().max() #gamma
+        quant_scaled_input = self.quantize_activations(input_norm,abs_max_x_value)
+
+        abs_mean_W_value = self.weight.abs().mean() #beta
+        ternarized_weights = self.ternarize_weights(abs_mean_W_value)
+
+        matmal_weight = F.linear(quant_scaled_input, ternarized_weights, self.bias)
+
+        beta_gamma = abs_mean_W_value * abs_max_x_value
+        output = matmal_weight * beta_gamma / self.Q_b
+        return output
+
+# class BitLinear158bNIQ(nn.Linear):
+#     def __init__(self, in_features, out_features, bias=False, bit_scale = 8):
+#         super(BitLinear158bNIQ, self).__init__(in_features, out_features, bias)
+#         self.bit_scale = bit_scale
+#         self.Q_b = 2 ** (self.bit_scale - 1)
+#         self.eps = 1e-8
+        
+#     def quantize_activations(self, input_norm, abs_max_x_value):
+#         scaled_x = torch.clamp(
+#             input_norm * self.Q_b / (abs_max_x_value + self.eps), -self.Q_b + self.eps, self.Q_b - self.eps
+#         )
+#         return scaled_x
+    
+#     def ternarize_weights(self,abs_mean_W_value):
+#         scaled_W = self.weight / (abs_mean_W_value + self.eps)
+#         quantize_weights = torch.sign(torch.clamp(scaled_W.round(), -1, 1))
+#         #STE 
+#         quantize_weights = (quantize_weights - self.weight).detach() + self.weight
+#         return quantize_weights
+
+#     def forward(self, input):
+#         input_norm = F.layer_norm(input, (self.in_features,))
+
+#         abs_mean_W_value = self.weight.abs().mean() #beta
+#         ternarized_weights = self.ternarize_weights(abs_mean_W_value)
+
+#         matmal_weight = F.linear(input_norm, ternarized_weights, self.bias)
+
+#         beta_gamma = abs_mean_W_value
+#         output = matmal_weight * beta_gamma / self.Q_b
+#         return output
+
+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 = BitLinear158b(config.n_embd, 3 * config.n_embd, bias=config.bias)
+        # output projection
+        self.c_proj = BitLinear158b(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 make GPU go brrrrr but support is only in PyTorch >= 2.0
+        self.flash = hasattr(torch.nn.functional, 'scaled_dot_product_attention')
+        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    = BitLinear158b(config.n_embd, 4 * config.n_embd, bias=config.bias)
+        self.gelu    = nn.GELU()
+        self.c_proj  = BitLinear158b(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 = self.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
+    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 = BitLinear158b(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, BitLinear158b):
+            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):
+        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) # shape (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 (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)
+
+        if targets is not None:
+            # if we are given some desired targets also calculate the loss
+            logits = self.lm_head(x)
+            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1), ignore_index=-1)
+        else:
+            # inference-time mini-optimization: only forward the lm_head on the very last position
+            logits = self.lm_head(x[:, [-1], :]) # note: using list [-1] to preserve the time dim
+            loss = None
+
+        return logits, loss
+
+    def crop_block_size(self, block_size):
+        # model surgery to decrease the block size if necessary
+        # e.g. we may load the GPT2 pretrained model checkpoint (block size 1024)
+        # but want to use a smaller block size for some smaller, simpler model
+        assert block_size <= self.config.block_size
+        self.config.block_size = block_size
+        self.transformer.wpe.weight = nn.Parameter(self.transformer.wpe.weight[:block_size])
+        for block in self.transformer.h:
+            if hasattr(block.attn, 'bias'):
+                block.attn.bias = block.attn.bias[:,:,:block_size,:block_size]
+
+    @classmethod
+    def from_pretrained(cls, model_type, override_args=None):
+        assert model_type in {'gpt2', 'gpt2-medium', 'gpt2-large', 'gpt2-xl'}
+        override_args = override_args or {} # default to empty dict
+        # only dropout can be overridden see more notes below
+        assert all(k == 'dropout' for k in override_args)
+        from transformers import GPT2LMHeadModel
+        print("loading weights from pretrained gpt: %s" % model_type)
+
+        # n_layer, n_head and n_embd are determined from model_type
+        config_args = {
+            'gpt2':         dict(n_layer=12, n_head=12, n_embd=768),  # 124M params
+            'gpt2-medium':  dict(n_layer=24, n_head=16, n_embd=1024), # 350M params
+            'gpt2-large':   dict(n_layer=36, n_head=20, n_embd=1280), # 774M params
+            'gpt2-xl':      dict(n_layer=48, n_head=25, n_embd=1600), # 1558M params
+        }[model_type]
+        print("forcing vocab_size=50257, block_size=1024, bias=True")
+        config_args['vocab_size'] = 50257 # always 50257 for GPT model checkpoints
+        config_args['block_size'] = 1024 # always 1024 for GPT model checkpoints
+        config_args['bias'] = True # always True for GPT model checkpoints
+        # we can override the dropout rate, if desired
+        if 'dropout' in override_args:
+            print(f"overriding dropout rate to {override_args['dropout']}")
+            config_args['dropout'] = override_args['dropout']
+        # create a from-scratch initialized minGPT model
+        config = GPTConfig(**config_args)
+        model = GPT(config)
+        sd = model.state_dict()
+        sd_keys = sd.keys()
+        sd_keys = [k for k in sd_keys if not k.endswith('.attn.bias')] # discard this mask / buffer, not a param
+
+        # init a huggingface/transformers model
+        model_hf = GPT2LMHeadModel.from_pretrained(model_type)
+        sd_hf = model_hf.state_dict()
+
+        # copy while ensuring all of the parameters are aligned and match in names and shapes
+        sd_keys_hf = sd_hf.keys()
+        sd_keys_hf = [k for k in sd_keys_hf if not k.endswith('.attn.masked_bias')] # ignore these, just a buffer
+        sd_keys_hf = [k for k in sd_keys_hf if not k.endswith('.attn.bias')] # same, just the mask (buffer)
+        transposed = ['attn.c_attn.weight', 'attn.c_proj.weight', 'mlp.c_fc.weight', 'mlp.c_proj.weight']
+        # basically the openai checkpoints use a "Conv1D" module, but we only want to use a vanilla Linear
+        # this means that we have to transpose these weights when we import them
+        assert len(sd_keys_hf) == len(sd_keys), f"mismatched keys: {len(sd_keys_hf)} != {len(sd_keys)}"
+        for k in sd_keys_hf:
+            if any(k.endswith(w) for w in transposed):
+                # special treatment for the Conv1D weights we need to transpose
+                assert sd_hf[k].shape[::-1] == sd[k].shape
+                with torch.no_grad():
+                    sd[k].copy_(sd_hf[k].t())
+            else:
+                # vanilla copy over the other parameters
+                assert sd_hf[k].shape == sd[k].shape
+                with torch.no_grad():
+                    sd[k].copy_(sd_hf[k])
+
+        return model
+
+    def configure_optimizers(self, weight_decay, learning_rate, betas, device_type):
+        # start with all of the candidate parameters
+        param_dict = {pn: p for pn, p in self.named_parameters()}
+        # filter out those that do not require grad
+        param_dict = {pn: p for pn, p in param_dict.items() if p.requires_grad}
+        # create optim groups. Any parameters that is 2D will be weight decayed, otherwise no.
+        # i.e. all weight tensors in matmuls + embeddings decay, all biases and layernorms don't.
+        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}
+        ]
+        num_decay_params = sum(p.numel() for p in decay_params)
+        num_nodecay_params = sum(p.numel() for p in nodecay_params)
+        print(f"num decayed parameter tensors: {len(decay_params)}, with {num_decay_params:,} parameters")
+        print(f"num non-decayed parameter tensors: {len(nodecay_params)}, with {num_nodecay_params:,} parameters")
+        # Create AdamW optimizer and use the fused version if it is available
+        fused_available = 'fused' in inspect.signature(torch.optim.AdamW).parameters
+        use_fused = fused_available and device_type == 'cuda'
+        extra_args = dict(fused=True) if use_fused else dict()
+        optimizer = torch.optim.AdamW(optim_groups, lr=learning_rate, betas=betas, **extra_args)
+        print(f"using fused AdamW: {use_fused}")
+
+        return optimizer
+
+    def estimate_mfu(self, fwdbwd_per_iter, dt):
+        """ estimate model flops utilization (MFU) in units of A100 bfloat16 peak FLOPS """
+        # first estimate the number of flops we do per iteration.
+        # see PaLM paper Appendix B as ref: https://arxiv.org/abs/2204.02311
+        N = self.get_num_params()
+        cfg = self.config
+        L, H, Q, T = cfg.n_layer, cfg.n_head, cfg.n_embd//cfg.n_head, cfg.block_size
+        flops_per_token = 6*N + 12*L*H*Q*T
+        flops_per_fwdbwd = flops_per_token * T
+        flops_per_iter = flops_per_fwdbwd * fwdbwd_per_iter
+        # express our flops throughput as ratio of A100 bfloat16 peak flops
+        flops_achieved = flops_per_iter * (1.0/dt) # per second
+        flops_promised = 312e12 # A100 GPU bfloat16 peak flops is 312 TFLOPS
+        mfu = flops_achieved / flops_promised
+        return mfu
+
+    @torch.no_grad()
+    def generate(self, idx, max_new_tokens, temperature=1.0, top_k=None):
+        """
+        Take a conditioning sequence of indices idx (LongTensor of shape (b,t)) and complete
+        the sequence max_new_tokens times, feeding the predictions back into the model each time.
+        Most likely you'll want to make sure to be in model.eval() mode of operation for this.
+        """
+        for _ in range(max_new_tokens):
+            # if the sequence context is growing too long we must crop it at block_size
+            idx_cond = idx if idx.size(1) <= self.config.block_size else idx[:, -self.config.block_size:]
+            # forward the model to get the logits for the index in the sequence
+            logits, _ = self(idx_cond)
+            # pluck the logits at the final step and scale by desired temperature
+            logits = logits[:, -1, :] / temperature
+            # optionally crop the logits to only the top k options
+            if top_k is not None:
+                v, _ = torch.topk(logits, min(top_k, logits.size(-1)))
+                logits[logits < v[:, [-1]]] = -float('Inf')
+            # apply softmax to convert logits to (normalized) probabilities
+            probs = F.softmax(logits, dim=-1)
+            # sample from the distribution
+            idx_next = torch.multinomial(probs, num_samples=1)
+            # append sampled index to the running sequence and continue
+            idx = torch.cat((idx, idx_next), dim=1)
+
+        return idx

sample.py

@@ -0,0 +1,77 @@
+"""
+Sample from a trained model
+"""
+import os
+import pickle
+from contextlib import nullcontext
+import torch
+# import tiktoken
+from model import GPTConfig, GPT
+
+# -----------------------------------------------------------------------------
+init_from = 'resume' # either 'resume' (from an out_dir) or a gpt2 variant (e.g. 'gpt2-xl')
+out_dir = 'out' # ignored if init_from is not 'resume'
+start = "\n" # or "<|endoftext|>" or etc. Can also specify a file, use as: "FILE:prompt.txt"
+num_samples = 10 # number of samples to draw
+max_new_tokens = 500 # number of tokens generated in each sample
+temperature = 0.8 # 1.0 = no change, < 1.0 = less random, > 1.0 = more random, in predictions
+top_k = 200 # retain only the top_k most likely tokens, clamp others to have 0 probability
+seed = 1337
+device = 'cuda' # examples: 'cpu', 'cuda', 'cuda:0', 'cuda:1', etc.
+dtype = 'bfloat16' if torch.cuda.is_available() and torch.cuda.is_bf16_supported() else 'float16' # 'float32' or 'bfloat16' or 'float16'
+compile = False # use PyTorch 2.0 to compile the model to be faster
+exec(open('configurator.py').read()) # overrides from command line or config file
+# -----------------------------------------------------------------------------
+
+torch.manual_seed(seed)
+torch.cuda.manual_seed(seed)
+torch.backends.cuda.matmul.allow_tf32 = True # allow tf32 on matmul
+torch.backends.cudnn.allow_tf32 = True # allow tf32 on cudnn
+device_type = 'cuda' if 'cuda' in device else 'cpu' # for later use in torch.autocast
+ptdtype = {'float32': torch.float32, 'bfloat16': torch.bfloat16, 'float16': torch.float16}[dtype]
+ctx = nullcontext() if device_type == 'cpu' else torch.amp.autocast(device_type=device_type, dtype=ptdtype)
+
+# model
+if init_from == 'resume':
+    # init from a model saved in a specific directory
+    ckpt_path = os.path.join(out_dir, 'ckpt.pt')
+    checkpoint = torch.load(ckpt_path, map_location=device)
+    gptconf = GPTConfig(**checkpoint['model_args'])
+    model = GPT(gptconf)
+    state_dict = checkpoint['model']
+    unwanted_prefix = '_orig_mod.'
+    for k,v in list(state_dict.items()):
+        if k.startswith(unwanted_prefix):
+            state_dict[k[len(unwanted_prefix):]] = state_dict.pop(k)
+    model.load_state_dict(state_dict)
+elif init_from.startswith('gpt2'):
+    # init from a given GPT-2 model
+    model = GPT.from_pretrained(init_from, dict(dropout=0.0))
+
+model.eval()
+model.to(device)
+if compile:
+    model = torch.compile(model) # requires PyTorch 2.0 (optional)
+
+# --- CUSTOM TOKENIZER PATCH ---
+from tokenizers import Tokenizer
+print("Loading custom_tokenizer.json...")
+enc = Tokenizer.from_file("data/lua/custom_tokenizer.json")
+encode = lambda s: enc.encode(s).ids
+decode = lambda l: enc.decode(l)
+# ------------------------------
+
+# encode the beginning of the prompt
+if start.startswith('FILE:'):
+    with open(start[5:], 'r', encoding='utf-8') as f:
+        start = f.read()
+start_ids = encode(start)
+x = (torch.tensor(start_ids, dtype=torch.long, device=device)[None, ...])
+
+# run generation
+with torch.no_grad():
+    with ctx:
+        for k in range(num_samples):
+            y = model.generate(x, max_new_tokens, temperature=temperature, top_k=top_k)
+            print(decode(y[0].tolist()))
+            print('---------------')