Akash kaothalkar

Can you please add the little more detailed explanation of the code and the self-distillation technique used to make it more efficient. Various parts of the code are somewhat hard...

This is good work, its something I really needed. Can you elaborate anywhere in the code more about what input (dimension wise) to each of the functions. I want to...

### Your current environment The output of `python collect_env.py` ```text Collecting environment information... PyTorch version: 2.7.0a0+gitd0f5df8 Is debug build: False CUDA used to build PyTorch: None ROCM used to build...