File size: 2,244 Bytes
3c62626 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 | import torch
import torch.nn as nn
from transformers import PreTrainedModel, GenerationMixin
from transformers.modeling_outputs import CausalLMOutput
from models.config import TinyGPTConfig
from models.transformer_block import TransformerBlock
class TinyGPT(PreTrainedModel, GenerationMixin):
config_class = TinyGPTConfig
def __init__(self, config):
super().__init__(config)
self.config = config
self.token_embedding = nn.Embedding(
config.vocab_size,
config.embed_dim,
)
self.position_embedding = nn.Embedding(
config.max_seq_len,
config.embed_dim,
)
self.transformer_blocks = nn.ModuleList([
TransformerBlock(
config.embed_dim
)
for _ in range(config.num_layers)
])
self.ln_f = nn.LayerNorm(
config.embed_dim
)
self.lm_head = nn.Linear(
config.embed_dim,
config.vocab_size,
)
self.post_init()
def forward(self, input_ids, **kwargs):
batch_size, seq_len = input_ids.shape
positions = torch.arange(
seq_len,
device=input_ids.device
)
token_emb = self.token_embedding(
input_ids
)
pos_emb = self.position_embedding(
positions
)
x = token_emb + pos_emb
for block in self.transformer_blocks:
x = block(x)
x = self.ln_f(x)
logits = self.lm_head(x)
return CausalLMOutput(logits=logits)
def prepare_inputs_for_generation(self, input_ids, **kwargs):
return {"input_ids": input_ids}
def _init_weights(self, module):
std = 0.02
if isinstance(module, nn.Linear):
module.weight.data.normal_(mean=0.0, std=std)
if module.bias is not None:
module.bias.data.zero_()
elif isinstance(module, nn.Embedding):
module.weight.data.normal_(mean=0.0, std=std)
elif isinstance(module, nn.LayerNorm):
module.bias.data.zero_()
module.weight.data.fill_(1.0)
TinyGPT.register_for_auto_class("AutoModelForCausalLM") |