docs: add notes about BOS and LoRA
Browse files
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.
|