Fantasy1120
Results
3
comments of
Fantasy1120
You can try to install torch==1.7.1
> Hi, I think this is acceptable. Different number of GPUs cause different gradient_accumulation_steps. Different types of GPUs cause randomness. Btw, the performance for phi-2-siglip-base we listed here is trained...
> Hello, I've been trying to reproduce the results in the paper but have been struggling to get the same results. Would you be able to share the configuration you...