IC-Yuan
Results
2
comments of
IC-Yuan
Hi, Have you solved this issue? I found that activation quantization generally does not converge, and sometimes it even performs worse after training than before training. For example: 10/12/2024 01:05:28...
Taking LDM as an example, it uses the `def ddim_sampling` function from `/q-diffusion/ldm/models/diffusion/ddim.py` for sampling. At the end of `def ddim_sampling`, it provides `intermediates`, which are the intermediate results at...