HSinghHuggingFace's picture
huggingface app
3aa6cf7
import torch
import torch.nn as nn
from torch.nn import functional as F
from .block import Block
import sys
import os
# Add the project root to Python path
sys.path.append(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))))
from src.config.model_config import GPTConfig
class GPT(nn.Module):
def __init__(self, config):
super().__init__()
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),
h = nn.ModuleList([Block(config) for _ in range(config.n_layer)]),
ln_f = nn.LayerNorm(config.n_embd),
))
self.lm_head = nn.Linear(config.n_embd, config.vocab_size, bias=False)
# weight sharing
self.transformer.wte.weight = self.lm_head.weight
# weight initialization
self.apply(self._init_weights)
def _init_weights(self, module):
if isinstance(module, nn.Linear):
std = 0.02
if hasattr(module, 'NANGPT_SCALE_INIT'):
std *= (2 * self.config.n_layer) ** -0.5
torch.nn.init.normal_(module.weight, mean=0.0, std=std)
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):
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=idx.device)
pos_emb = self.transformer.wpe(pos)
tok_emb = self.transformer.wte(idx)
x = tok_emb + pos_emb
for block in self.transformer.h:
x = block(x)
x = self.transformer.ln_f(x)
logits = self.lm_head(x)
loss = None
if targets is not None:
loss = F.cross_entropy(logits.view(-1, logits.size(-1)), targets.view(-1))
return logits, loss
@classmethod
def from_pretrained(cls, model_type):
"""Loads pretrained GPT-2 model weights from huggingface"""
assert model_type in {'gpt2', 'gpt2-medium', 'gpt2-large', 'gpt2-xl'}
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]
config_args['vocab_size'] = 50257 # always 50257 for GPT model checkpoints
config_args['block_size'] = 1024 # always 1024 for GPT model checkpoints
# 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']
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