facebookresearch/ParlAI

Self-Chat Improvements

Open

#2.221 geöffnet am 24. Nov. 2019

Auf GitHub ansehen
 (2 Kommentare) (0 Reaktionen) (1 zugewiesene Person)Python (2.089 Forks)batch import
EnhancementH1 2020Help Wanteddonotreap

Repository-Metriken

Stars
 (10.371 Stars)
PR-Merge-Metriken
 (Keine gemergten PRs in 30 T)

Beschreibung

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.

Contributor Guide