Has anyone had success running this model with a 7900XTX on WSL2(Ubuntu)?
cant get this to run, its getting stuck at "loading pipeline components" and I get these two warnings:
/home/user/.local/lib/python3.10/site-packages/torch/cuda/init.py:702: UserWarning: Can't initialize amdsmi - Error code: 34
warnings.warn(f"Can't initialize amdsmi - Error code: {e.err_code}")You set
add_prefix_space. The tokenizer needs to be converted from the slow tokenizers
https://gist.github.com/damico/484f7b0a148a0c5f707054cf9c0a0533, I used this script but it didnt find any errors with my installations.
PC Specs: 24GB Vram and 32GB Ram
I'm having the exact same issue.
I have been troubleshooting for days I can't figure it out... Its outside my expertise....
Exact same issue:
Loading checkpoint shards: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████ 2/2 [00:00<00:00, 12.79it/s]
Loading pipeline components...: 57%|██████████████████████████████████████████████████████████████████████████████████████████▎ | 4/7 [00:01<00:00, 3.07it/s]You set add_prefix_space. The tokenizer needs to be converted from the slow tokenizers
Loading pipeline components...: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 7/7 [00:01<00:00, 3.63it/s]
Same issue here but I using a gtx 4070. I think WSL2 is the issue.