(self)
| 89 | return out |
| 90 | |
| 91 | def reset_parameters(self): |
| 92 | self.attention_norm.reset_parameters() |
| 93 | self.attention.reset_parameters() |
| 94 | self.ffn_norm.reset_parameters() |
| 95 | self.feed_forward.reset_parameters() |
| 96 | |
| 97 | |
| 98 | # A toy transformer model, partly inspired by the nanoGPT model: |
nothing calls this directly
no test coverage detected