facebookresearch/ParlAI

Self-Chat Improvements

Open

#2,221 创建于 2019年11月24日

在 GitHub 查看
 (2 评论) (0 反应) (1 负责人)Python (2,089 fork)batch import
EnhancementH1 2020Help Wanteddonotreap

仓库指标

Star
 (10,371 star)
PR 合并指标
 (30 天内没有已合并 PR)

描述

Each of these could be spun into a sub-issue, and requires some scoping to be done. The following improvements could benefit self-chat in particular.

  • Allow 2 models to be passed in e.g. apprentice, wizard, currently can't.
  • Currently does not support standard batchworld (will need the world not to do anything fancy, maybe it's possible? This would be easier if batchworld accepted a generic 'contextWorld' with initial contexts, but we don't have that currently (we have talked about this for a while).
  • General fix (beyond self-chat) but useful here: allow worlds to have args (currently only teachers are checked) so we can add flags more easily..
  • Make interactive world share more with self-chat world where possible via inheritance.

贡献者指南