- 20 Jan, 2024 2 commits
-
-
Zhen Li authored
-
bytesurfer3 authored
The modification replaces this method with a token-based approach using a tokenizer. This tokenizes the entire prompt, identifies the token corresponding to the trigger word, removes it, and then decodes the modified tokens back into text.
-
- 17 Jan, 2024 1 commit
-
-
Paper99 authored
-
- 15 Jan, 2024 1 commit
-
-
Paper99 authored
-