BotBot6990/Dirty-Muse-1-Million-Context

I have not extensively tested with long games, but with the testing I have done it seems to hold up well.

I extended the context to better handle games as the short context limit would end games quickly.

I advise testing the context to see what your system can handle.

All testing was done in Oobabooga TextGen. Results of my tests are as follows.

I take no credit for the creation of this model.