You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Essentially changing the LLM template dynamically at program execution. Add a parameter that reads a file and changes the corresponding variables. Especially useful if using various different LLMs. This needs some research first, as I know pretty much nothing about the templates.
The text was updated successfully, but these errors were encountered:
I could also add an option to not use files, use parameters or something. Perhaps reconverting everything with a modified tokenizer.json could be also a good option, for having the same template for every converted model
Essentially changing the LLM template dynamically at program execution. Add a parameter that reads a file and changes the corresponding variables. Especially useful if using various different LLMs. This needs some research first, as I know pretty much nothing about the templates.
The text was updated successfully, but these errors were encountered: