| #GPT2 Params | |
| from dataclasses import dataclass | |
| class GPTConfig: | |
| block_size: int = 1024 | |
| n_embd : int = 768 | |
| n_head : int = 12 | |
| n_layer : int = 12 | |
| vocab_size : int = 50304 |
| #GPT2 Params | |
| from dataclasses import dataclass | |
| class GPTConfig: | |
| block_size: int = 1024 | |
| n_embd : int = 768 | |
| n_head : int = 12 | |
| n_layer : int = 12 | |
| vocab_size : int = 50304 |