first time poster here so please forgive me and correct me on my posting mistakes...
Im trying to teach the databricks/dolly-v2-3b llm, some data, which is just one sentence.
In the future I would like to be able to teach it larger amount of text.
Thing is I have gone through a tutorial from Sam Witteveen on YT, and everything execute OK, just that if I ask in prompt a question regarding my one sentence data, I get some weird answer... not only that but even if I prompt "Hi", i get a weid answer, but when using databricks/dolly-v2-3b in vanilla form I get an answer "Hello." if I prompt "Hi".
Enter your input (or 'q' to quit): hi
A decoder-only architecture is being used, but right-padding was detected! For correct generation results, please set `padding_side='left'` when initializing the tokenizer.
Model's response: fallCommentCommentCommentCommentCommentCommentCommentCommentakingatformatformatform],[@ 83atformreek Victoriaсп Victoriaсп Victoriaсп Victoriaсп Victoriaсп Victoriaсп Victoriaсп Victoriaсп Victoriaсп Victoria442fall pulled}(}(}(}(}(}(}(}(}(}(}(}(}(}(}(}(}(}( associateaxel二 Victoria yabatimylated unfortunate grievances PresFinding browyster}( associateaxel二 Victoria yabatimylated unfortunate grievances choirignignignignignignignignignignignignignignignign Borgramble
Can anyone direct me to where my issue might be?
