def step_core()

in lm_human_preferences/policy.py [0:0]

• 20 lines of code
• 1 McCabe index (conditional complexity)

    def step_core(self, model_hparams, tokens, past=None, past_tokens=None, do_dropout=False, name=None):
        with tf.name_scope(name, 'step'):
            with tf.variable_scope(
                    self.scope,
                    reuse=self.built,
                    auxiliary_name_scope=not self.built,
                    use_resource=self.use_resource):
                lm_output = self.model(X=tokens, past=past, past_tokens=past_tokens,
                                       do_dropout=do_dropout, padding_token=self.padding_token)

                # need to slice logits since we don't want to generate special tokens
                logits = lm_output['lm_logits'][:,:,:self.model_hparams.n_vocab]
                presents = lm_output['present']
                value = lm_output['value']
                if not self.built:
                    self._set_initializers()
                self.built = True
                return {
                    'logits': logits,
                    'values': value,
                    'presents': presents,
                }