11b commited on
Commit
5b10150
1 Parent(s): 74cfaba

docs: add notes about BOS and LoRA

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -102,6 +102,11 @@ Which might generate something like:
102
 
103
  Same process applies. Usually, it is best to do a sliding window over the user and model turns, but keep the system prompt fixed at the start of the context window.
104
 
 
 
 
 
 
105
  ## Limitations and biases
106
 
107
  The intended use-case for this model is fictional writing for entertainment purposes. Any other sort of usage is out of scope.
 
102
 
103
  Same process applies. Usually, it is best to do a sliding window over the user and model turns, but keep the system prompt fixed at the start of the context window.
104
 
105
+ ## Other notes
106
+
107
+ - When prompted correctly, the model will always start by generating a BOS token. This behavior is an accidental side-effect which we plan to address in future model versions and should not be relied upon.
108
+ - The model was trained as a LoRA with a somewhat unorthodox configuration which causes errors when used with the current version of `peft`, hence we release it as a full model instead.
109
+
110
  ## Limitations and biases
111
 
112
  The intended use-case for this model is fictional writing for entertainment purposes. Any other sort of usage is out of scope.