Open Kyeongpil opened 2 weeks ago
Thanks for your kind comments! We haven't planned to implement the quantized version of Adam-mini recently, but it is definitely an important direction to pursue and implement. :D
Did just want to ask the same, and Adam4Bit and a Adam8bit :-)
Perhaps it's worth pursuing if it's possible to extend the bitsandbytes base optimizer class so that we can get 8bit quantization as well as paged memory support as well? https://github.com/TimDettmers/bitsandbytes/blob/main/bitsandbytes/optim/optimizer.py
Perhaps it's worth pursuing if it's possible to extend the bitsandbytes base optimizer class so that we can get 8bit quantization as well as paged memory support as well? https://github.com/TimDettmers/bitsandbytes/blob/main/bitsandbytes/optim/optimizer.py
Thanks for the great suggestion! We will work on it!
Hello, I greatly appreciate your excellent work.
As you discussed in the paper, I believe incorporating quantization methods like Adam8Bit could further enhance the results .
Do you have any plans to implement a quantized version of Adam-mini in the near future?
Thank you for your consideration.