first commit, refer to huggingface pytorch-pretrained-BERT in code

Author: graykode

.gitignore

@@ -1,2 +1,5 @@
 .idea
 venv
+models
+gpt2-pytorch_model.bin
+__pycache__

GPT2/config.py

@@ -0,0 +1,25 @@
+'''
+    code by TaeHwan Jung(@graykode)
+    Original Paper and repository here : https://github.com/openai/gpt-2
+    GPT2 Pytorch Model : https://github.com/huggingface/pytorch-pretrained-BERT
+'''
+class GPT2Config(object):
+    def __init__(
+            self,
+            vocab_size_or_config_json_file=50257,
+            n_positions=1024,
+            n_ctx=1024,
+            n_embd=768,
+            n_layer=12,
+            n_head=12,
+            layer_norm_epsilon=1e-5,
+            initializer_range=0.02,
+    ):
+        self.vocab_size = vocab_size_or_config_json_file
+        self.n_ctx = n_ctx
+        self.n_positions = n_positions
+        self.n_embd = n_embd
+        self.n_layer = n_layer
+        self.n_head = n_head
+        self.layer_norm_epsilon = layer_norm_epsilon
+        self.initializer_range = initializer_range

GPT2/encoder.json

@@ -104,10 +104,10 @@ def decode(self, tokens):
         text = bytearray([self.byte_decoder[c] for c in text]).decode('utf-8', errors=self.errors)
         return text
 
-def get_encoder(model_name):
-    with open(os.path.join('models', model_name, 'encoder.json'), 'r') as f:
+def get_encoder():
+    with open(os.path.join('encoder.json'), 'r') as f:
         encoder = json.load(f)
-    with open(os.path.join('models', model_name, 'vocab.bpe'), 'r', encoding="utf-8") as f:
+    with open(os.path.join('vocab.bpe'), 'r', encoding="utf-8") as f:
         bpe_data = f.read()
     bpe_merges = [tuple(merge_str.split()) for merge_str in bpe_data.split('\n')[1:-1]]
     return Encoder(

encoder.py renamed to GPT2/encoder.py

@@ -0,0 +1,210 @@
+'''
+    code by TaeHwan Jung(@graykode)
+    Original Paper and repository here : https://github.com/openai/gpt-2
+    GPT2 Pytorch Model : https://github.com/huggingface/pytorch-pretrained-BERT
+'''
+import copy
+import torch
+import math
+import torch.nn as nn
+from torch.nn.parameter import Parameter
+
+def gelu(x):
+    return 0.5 * x * (1 + torch.tanh(math.sqrt(2 / math.pi) * (x + 0.044715 * torch.pow(x, 3))))
+
+class LayerNorm(nn.Module):
+    def __init__(self, hidden_size, eps=1e-12):
+        """Construct a layernorm module in the TF style (epsilon inside the square root).
+        """
+        super(LayerNorm, self).__init__()
+        self.weight = nn.Parameter(torch.ones(hidden_size))
+        self.bias = nn.Parameter(torch.zeros(hidden_size))
+        self.variance_epsilon = eps
+
+    def forward(self, x):
+        u = x.mean(-1, keepdim=True)
+        s = (x - u).pow(2).mean(-1, keepdim=True)
+        x = (x - u) / torch.sqrt(s + self.variance_epsilon)
+        return self.weight * x + self.bias
+
+class Conv1D(nn.Module):
+    def __init__(self, nf, nx):
+        super(Conv1D, self).__init__()
+        self.nf = nf
+        w = torch.empty(nx, nf)
+        nn.init.normal_(w, std=0.02)
+        self.weight = Parameter(w)
+        self.bias = Parameter(torch.zeros(nf))
+
+    def forward(self, x):
+        size_out = x.size()[:-1] + (self.nf,)
+        x = torch.addmm(self.bias, x.view(-1, x.size(-1)), self.weight)
+        x = x.view(*size_out)
+        return x
+
+class Attention(nn.Module):
+    def __init__(self, nx, n_ctx, config, scale=False):
+        super(Attention, self).__init__()
+        n_state = nx  # in Attention: n_state=768 (nx=n_embd)
+        # [switch nx => n_state from Block to Attention to keep identical to TF implem]
+        assert n_state % config.n_head == 0
+        self.register_buffer("bias", torch.tril(torch.ones(n_ctx, n_ctx)).view(1, 1, n_ctx, n_ctx))
+        self.n_head = config.n_head
+        self.split_size = n_state
+        self.scale = scale
+        self.c_attn = Conv1D(n_state * 3, nx)
+        self.c_proj = Conv1D(n_state, nx)
+
+    def _attn(self, q, k, v):
+        w = torch.matmul(q, k)
+        if self.scale:
+            w = w / math.sqrt(v.size(-1))
+        nd, ns = w.size(-2), w.size(-1)
+        b = self.bias[:, :, ns-nd:ns, :ns]
+        w = w * b - 1e10 * (1 - b)
+        w = nn.Softmax(dim=-1)(w)
+        return torch.matmul(w, v)
+
+    def merge_heads(self, x):
+        x = x.permute(0, 2, 1, 3).contiguous()
+        new_x_shape = x.size()[:-2] + (x.size(-2) * x.size(-1),)
+        return x.view(*new_x_shape)  # in Tensorflow implem: fct merge_states
+
+    def split_heads(self, x, k=False):
+        new_x_shape = x.size()[:-1] + (self.n_head, x.size(-1) // self.n_head)
+        x = x.view(*new_x_shape)  # in Tensorflow implem: fct split_states
+        if k:
+            return x.permute(0, 2, 3, 1)  # (batch, head, head_features, seq_length)
+        else:
+            return x.permute(0, 2, 1, 3)  # (batch, head, seq_length, head_features)
+
+    def forward(self, x, layer_past=None):
+        x = self.c_attn(x)
+        query, key, value = x.split(self.split_size, dim=2)
+        query = self.split_heads(query)
+        key = self.split_heads(key, k=True)
+        value = self.split_heads(value)
+        if layer_past is not None:
+            past_key, past_value = layer_past[0].transpose(-2, -1), layer_past[1]  # transpose back cf below
+            key = torch.cat((past_key, key), dim=-1)
+            value = torch.cat((past_value, value), dim=-2)
+        present = torch.stack((key.transpose(-2, -1), value))  # transpose to have same shapes for stacking
+        a = self._attn(query, key, value)
+        a = self.merge_heads(a)
+        a = self.c_proj(a)
+        return a, present
+
+class MLP(nn.Module):
+    def __init__(self, n_state, config):  # in MLP: n_state=3072 (4 * n_embd)
+        super(MLP, self).__init__()
+        nx = config.n_embd
+        self.c_fc = Conv1D(n_state, nx)
+        self.c_proj = Conv1D(nx, n_state)
+        self.act = gelu
+
+    def forward(self, x):
+        h = self.act(self.c_fc(x))
+        h2 = self.c_proj(h)
+        return h2
+
+class Block(nn.Module):
+    def __init__(self, n_ctx, config, scale=False):
+        super(Block, self).__init__()
+        nx = config.n_embd
+        self.ln_1 = LayerNorm(nx, eps=config.layer_norm_epsilon)
+        self.attn = Attention(nx, n_ctx, config, scale)
+        self.ln_2 = LayerNorm(nx, eps=config.layer_norm_epsilon)
+        self.mlp = MLP(4 * nx, config)
+
+    def forward(self, x, layer_past=None):
+        a, present = self.attn(self.ln_1(x), layer_past=layer_past)
+        x = x + a
+        m = self.mlp(self.ln_2(x))
+        x = x + m
+        return x, present
+
+class GPT2Model(nn.Module):
+    def __init__(self, config):
+        super(GPT2Model, self).__init__()
+        self.n_layer = config.n_layer
+        self.n_embd = config.n_embd
+        self.n_vocab = config.vocab_size
+
+        self.wte = nn.Embedding(config.vocab_size, config.n_embd)
+        self.wpe = nn.Embedding(config.n_positions, config.n_embd)
+        block = Block(config.n_ctx, config, scale=True)
+        self.h = nn.ModuleList([copy.deepcopy(block) for _ in range(config.n_layer)])
+        self.ln_f = LayerNorm(config.n_embd, eps=config.layer_norm_epsilon)
+
+    def set_embeddings_weights(self, model_embeddings_weights):
+        embed_shape = model_embeddings_weights.shape
+        self.decoder = nn.Linear(embed_shape[1], embed_shape[0], bias=False)
+        self.decoder.weight = model_embeddings_weights  # Tied weights
+
+    def forward(self, input_ids, position_ids=None, token_type_ids=None, past=None):
+        if past is None:
+            past_length = 0
+            past = [None] * len(self.h)
+        else:
+            past_length = past[0][0].size(-2)
+        if position_ids is None:
+            position_ids = torch.arange(past_length, input_ids.size(-1) + past_length, dtype=torch.long,
+                                        device=input_ids.device)
+            position_ids = position_ids.unsqueeze(0).expand_as(input_ids)
+
+        input_shape = input_ids.size()
+        input_ids = input_ids.view(-1, input_ids.size(-1))
+        position_ids = position_ids.view(-1, position_ids.size(-1))
+
+        inputs_embeds = self.wte(input_ids)
+        position_embeds = self.wpe(position_ids)
+        if token_type_ids is not None:
+            token_type_ids = token_type_ids.view(-1, token_type_ids.size(-1))
+            token_type_embeds = self.wte(token_type_ids)
+        else:
+            token_type_embeds = 0
+        hidden_states = inputs_embeds + position_embeds + token_type_embeds
+        presents = []
+        for block, layer_past in zip(self.h, past):
+            hidden_states, present = block(hidden_states, layer_past)
+            presents.append(present)
+        hidden_states = self.ln_f(hidden_states)
+        output_shape = input_shape + (hidden_states.size(-1),)
+        return hidden_states.view(*output_shape), presents
+
+class GPT2LMHead(nn.Module):
+    def __init__(self, model_embeddings_weights, config):
+        super(GPT2LMHead, self).__init__()
+        self.n_embd = config.n_embd
+        self.set_embeddings_weights(model_embeddings_weights)
+
+    def set_embeddings_weights(self, model_embeddings_weights):
+        embed_shape = model_embeddings_weights.shape
+        self.decoder = nn.Linear(embed_shape[1], embed_shape[0], bias=False)
+        self.decoder.weight = model_embeddings_weights  # Tied weights
+
+    def forward(self, hidden_state):
+        # Truncated Language modeling logits (we remove the last token)
+        # h_trunc = h[:, :-1].contiguous().view(-1, self.n_embd)
+        lm_logits = self.decoder(hidden_state)
+        return lm_logits
+
+class GPT2LMHeadModel(nn.Module):
+    def __init__(self, config):
+        super(GPT2LMHeadModel, self).__init__()
+        self.transformer = GPT2Model(config)
+        self.lm_head = GPT2LMHead(self.transformer.wte.weight, config)
+
+    def set_tied(self):
+        """ Make sure we are sharing the embeddings
+        """
+        self.lm_head.set_embeddings_weights(self.transformer.wte.weight)
+
+    def forward(self, input_ids, position_ids=None, token_type_ids=None, lm_labels=None, past=None):
+        hidden_states, presents = self.transformer(input_ids, position_ids, token_type_ids, past)
+        lm_logits = self.lm_head(hidden_states)
+        if lm_labels is not None:
+            loss_fct = nn.CrossEntropyLoss(ignore_index=-1)
+            loss = loss_fct(lm_logits.view(-1, lm_logits.size(-1)), lm_labels.view(-1))
+            return loss
+        return lm_logits, presents

GPT2/model.py

@@ -0,0 +1,38 @@
+'''
+    code by TaeHwan Jung(@graykode)
+    Original Paper and repository here : https://github.com/openai/gpt-2
+    GPT2 Pytorch Model : https://github.com/huggingface/pytorch-pretrained-BERT
+'''
+import torch
+import torch.nn.functional as F
+from tqdm import trange
+
+def top_k_logits(logits, k):
+    if k == 0:
+        return logits
+    values, _ = torch.topk(logits, k)
+    min_values = values[:, -1]
+    return torch.where(logits < min_values, torch.ones_like(logits, dtype=logits.dtype) * -1e10, logits)
+
+def sample_sequence(model, length, start_token=None, batch_size=None, context=None, temperature=1, top_k=0, device='cuda', sample=True):
+    if start_token is None:
+        assert context is not None, 'Specify exactly one of start_token and context!'
+        context = torch.tensor(context, device=device, dtype=torch.long).unsqueeze(0).repeat(batch_size, 1)
+    else:
+        assert context is None, 'Specify exactly one of start_token and context!'
+        context = torch.full((batch_size, 1), start_token, device=device, dtype=torch.long)
+    prev = context
+    output = context
+    past = None
+    with torch.no_grad():
+        for i in trange(length):
+            logits, past = model(prev, past=past)
+            logits = logits[:, -1, :] / temperature
+            logits = top_k_logits(logits, k=top_k)
+            log_probs = F.softmax(logits, dim=-1)
+            if sample:
+                prev = torch.multinomial(log_probs, num_samples=1)
+            else:
+                _, prev = torch.topk(log_probs, k=1, dim=-1)
+            output = torch.cat((output, prev), dim=1)
+    return output

GPT2/sample.py

@@ -0,0 +1,52 @@
+'''
+    code by TaeHwan Jung(@graykode)
+    Original Paper and repository here : https://github.com/openai/gpt-2
+    GPT2 Pytorch Model : https://github.com/huggingface/pytorch-pretrained-BERT
+'''
+import logging
+
+logger = logging.getLogger(__name__)
+
+def load_weight(model, state_dict):
+    old_keys = []
+    new_keys = []
+    for key in state_dict.keys():
+        new_key = None
+        if key.endswith(".g"):
+            new_key = key[:-2] + ".weight"
+        elif key.endswith(".b"):
+            new_key = key[:-2] + ".bias"
+        elif key.endswith(".w"):
+            new_key = key[:-2] + ".weight"
+        if new_key:
+            old_keys.append(key)
+            new_keys.append(new_key)
+    for old_key, new_key in zip(old_keys, new_keys):
+        state_dict[new_key] = state_dict.pop(old_key)
+
+    missing_keys = []
+    unexpected_keys = []
+    error_msgs = []
+    # copy state_dict so _load_from_state_dict can modify it
+    metadata = getattr(state_dict, "_metadata", None)
+    state_dict = state_dict.copy()
+    if metadata is not None:
+        state_dict._metadata = metadata
+
+    def load(module, prefix=""):
+        local_metadata = {} if metadata is None else metadata.get(prefix[:-1], {})
+        module._load_from_state_dict(
+            state_dict, prefix, local_metadata, True, missing_keys, unexpected_keys, error_msgs
+        )
+        for name, child in module._modules.items():
+            if child is not None:
+                load(child, prefix + name + ".")
+
+    start_model = model
+    if hasattr(model, "transformer") and all(not s.startswith('transformer.') for s in state_dict.keys()):
+        start_model = model.transformer
+    load(start_model, prefix="")
+
+    # Make sure we are still sharing the output and input embeddings after loading weights
+    model.set_tied()
+    return model