Implementation of the gelu activation function. For information: OpenAI GPT's gelu is slightly different (and gives slightly different results): 0.5 * x * (1 + torch.tanh(math.sqrt(2 / math.pi) * (x + 0.044715 * torch.pow(x, 3))))
(x)
| 149 | |
| 150 | |
| 151 | def gelu(x): |
| 152 | """Implementation of the gelu activation function. |
| 153 | For information: OpenAI GPT's gelu is slightly different (and gives slightly different results): |
| 154 | 0.5 * x * (1 + torch.tanh(math.sqrt(2 / math.pi) * (x + 0.044715 * torch.pow(x, 3)))) |
| 155 | """ |
| 156 | return x * 0.5 * (1.0 + torch.erf(x / math.sqrt(2.0))) |
| 157 | |
| 158 | |
| 159 | def swish(x): |
nothing calls this directly
no outgoing calls
no test coverage detected