You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Are you using cpu_offloading=True parameter? As mentioned below: #23
yes i used cpu_offloading=True and i have 24gb of ram and 12gb of vram. when it is trying to load models i getting like this: (myenv) sathvik@sathvik:/mnt/c/Users/pasun/Music/Pyramid-Flow$ python app.py
Model directory '/mnt/c/Users/pasun/Music/Pyramid-Flow/pyramid_flow_model' already exists. Skipping download.
using half precision
Using temporal causal attention
We interp the position embedding of condition latents
You set add_prefix_space. The tokenizer needs to be converted from the slow tokenizers
Loading checkpoint shards: 50%|█████████████████████████████ | 1/2 [00:45<00:45, 45.82s/it]Killed
No description provided.
The text was updated successfully, but these errors were encountered: