Floating point exception

[Jamie-Cheung]

image tokenizer is loaded
Choose adapter size: base
condition type: seg
gpt model is loaded
no need to compile model in demo
checkpoints/t5-ckpt/flan-t5-xl
Loading checkpoint shards: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:11<00:00, 5.94s/it]
processing left-padding...
prompt 0 token len: 8
prompt 1 token len: 8
Floating point exception

If anyone encountered this error？

[Jamie-Cheung]

image tokenizer is loaded Choose adapter size: base condition type: seg gpt model is loaded no need to compile model in demo checkpoints/t5-ckpt/flan-t5-xl Loading checkpoint shards: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:11<00:00, 5.94s/it] processing left-padding... prompt 0 token len: 8 prompt 1 token len: 8 Floating point exception

If anyone encountered this error？

It can be solved by set ” parser.add_argument("--precision", type=str, default='none', choices=["none", "fp16", "bf16"]) “