runtime error

Exit code: 1. Reason: vision_tower, self.forward_kwargs = self.build_vision_tower( ~~~~~~~~~~~~~~~~~~~~~~~^ vision_tower_params ^^^^^^^^^^^^^^^^^^^ ) ^ File "/usr/local/lib/python3.13/site-packages/janus/models/clip_encoder.py", line 73, in build_vision_tower vision_tower = create_siglip_vit(**vision_tower_params) File "/usr/local/lib/python3.13/site-packages/janus/models/siglip_vit.py", line 658, in create_siglip_vit model = VisionTransformer( img_size=image_size, ...<9 lines>... num_classes=0, ) File "/usr/local/lib/python3.13/site-packages/janus/models/siglip_vit.py", line 391, in __init__ x.item() for x in torch.linspace(0, drop_path_rate, depth) ~~~~~~^^ File "/usr/local/lib/python3.13/site-packages/torch/utils/_device.py", line 109, in __torch_function__ return func(*args, **kwargs) File "/usr/local/lib/python3.13/site-packages/torch/_meta_registrations.py", line 7779, in meta_local_scalar_dense raise RuntimeError("Tensor.item() cannot be called on meta tensors") RuntimeError: Tensor.item() cannot be called on meta tensors model.safetensors: 0%| | 0.00/4.18G [00:00<?, ?B/s] model.safetensors: 0%| | 131k/4.18G [00:01<15:10:01, 76.5kB/s] model.safetensors: 1%| | 40.2M/4.18G [00:02<03:48, 18.1MB/s]  model.safetensors: 6%|▋ | 267M/4.18G [00:03<00:41, 94.1MB/s]  model.safetensors: 10%|▉ | 417M/4.18G [00:04<00:33, 111MB/s]  model.safetensors: 22%|██▏ | 935M/4.18G [00:06<00:13, 236MB/s] model.safetensors: 28%|██▊ | 1.18G/4.18G [00:07<00:15, 191MB/s] model.safetensors: 51%|█████ | 2.13G/4.18G [00:08<00:05, 387MB/s] model.safetensors: 62%|██████▏ | 2.59G/4.18G [00:10<00:04, 358MB/s] model.safetensors: 84%|████████▍ | 3.52G/4.18G [00:11<00:01, 486MB/s] model.safetensors: 100%|██████████| 4.18G/4.18G [00:12<00:00, 341MB/s]

Container logs: