LevanKvirkvelia
/ nanoBERT.py
Last active
February 14, 2024 23:25
nanoBERT, inspired by @karpathy's nanoGPT
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import torch.nn as nn | |
| import torch.nn.functional as F | |
| import math | |
| from typing import Optional, Tuple | |
| class BertSelfAttention(nn.Module): | |
| def __init__(self, config): | |
| super().__init__() | |
| if config.hidden_size % config.num_attention_heads != 0: |