src/sal/models/reward_models.py [184:192]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                ans_list = ans.split("\n\n")
                for k in range(len(ans_list)):
                    if k == 0:
                        # TODO: add the system prompt like we did for math shepard?
                        text = question + " " + ans_list[0]
                    else:
                        text = ans_list[k]
                    conversation.append({"content": text, "role": "user"})
                    conversation.append({"content": "+", "role": "assistant"})
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/sal/models/reward_models.py [229:236]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
                ans_list = ans.split("\n\n")
                for k in range(len(ans_list)):
                    if k == 0:
                        text = question + " " + ans_list[0]
                    else:
                        text = ans_list[k]
                    conversation.append({"content": text, "role": "user"})
                    conversation.append({"content": "+", "role": "assistant"})
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -