def analyze_responses_op()

in lm_human_preferences/policy.py [0:0]

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

    def analyze_responses_op(self, queries, responses):
        contexts = self.embed_queries(queries)
        context_length = tf.shape(contexts)[1]
        tokens = tf.concat([contexts, responses], axis=1)
        result = self.step_core(self.model_hparams, tokens)
        logits = result['logits'][:, context_length-1:-1]

        logits /= self.temperature
        return dict(
            logprobs = utils.logprobs_from_logits(logits=logits, labels=responses),
            entropies = utils.entropy_from_logits(logits),
            values = result['values'][:, context_length-1:-1],
        )