Method greedy_until

test/general/lm_eval/models/textsynth.py:119–148

(self, requests)

        )

    def greedy_until(self, requests):
        if not requests:
            return []

        res = []
        for request in tqdm(requests):
            inp = request[0]
            request_args = request[1]
            until = request_args["until"]
            response = textsynth_completion(
                url=self.api_url + "/v1/engines/" + self.engine + "/completions",
                headers={"Authorization": "Bearer " + self.api_key},
                json={
                    "prompt": inp,
                    "max_tokens": self.max_gen_toks,
                    "top_k": 1,
                    "stop": until,
                },
            )
            resp = response.json()
            if "text" in resp:
                s = resp["text"]
                res.append(s)
            else:
                logger.error(
                    f"The following response does not contain generated `text`. "
                    "Got:\n{resp}"
                )
                assert False
        return res

    def _model_call(self, inps):
        # Isn't used because we override _loglikelihood_tokens