Envoid
/

Bacchus-22B

Text Generation

text-generation-inference

Model card Files Files and versions

Envoid commited on Aug 13, 2023

Commit

5cd14ab

·

1 Parent(s): e215b8b

Update README.md

Files changed (1) hide show

README.md +1 -2

README.md CHANGED Viewed

@@ -11,5 +11,4 @@ The initial results were a surprisingly coherent and functional model although I
 It responds well to Alpaca instruct style prompt formatting.
 It can be a little rude at times and doesn't have Dendrite's ego and thirst for philosophical discussion but I feel that it's overall it's a much better general purpose model.
-If you are role playing using the SillyTavern+SimpleProxy stack I would highly recommend the singleline.mjs prompt format otherwise it has a tendency to frequently run away with the entire scenario in one message.
-I had to add a bunch of junk tokens to contend with a vocabulary mismatch likely due to some of the novel features of the donor model.

 It responds well to Alpaca instruct style prompt formatting.
 It can be a little rude at times and doesn't have Dendrite's ego and thirst for philosophical discussion but I feel that it's overall it's a much better general purpose model.
+If you are role playing using the SillyTavern+SimpleProxy stack it does have a tendency to run away with a scene when using the verbose.mjs prompt format. The singleline.mjs format sometimes remedies this issue however it also causes some characters to give very short, dull replies. So achieving a balance might require a complete new custom prompt format.