Is the accuracy reported in the paper the result with finetuning applied? #203
Description
I have the following questions.
I know you must be busy, but I would truly appreciate it if you could find the time to respond.
- Are the perplexity and accuracy results reported in Tables 2, 3, 4, 5, and 6 of the paper obtained after finetuning?
- If so, I would like to know whether it is end-to-end or layer-wise finetuning.
- Additionally, I am not sure how to implement the finetuning step after vector quantization in code, so I would greatly appreciate any hints or guidance on this.
- Finally, if you have any insight into the difference in effectiveness between LoRA finetuning and the end-to-end or layer-wise finetuning described in the paper, I would be grateful if you could share that as well.