runtime error

Exit code: 1. Reason: [00:02<00:00, 581MB/s]  Fetching 8 files: 62%|██████▎ | 5/8 [00:04<00:02, 1.17it/s] Fetching 8 files: 100%|██████████| 8/8 [00:04<00:00, 1.87it/s] Download complete: 100%|██████████| 1.58G/1.58G [00:04<00:00, 581MB/s]  config.json: 0%| | 0.00/1.24k [00:00<?, ?B/s] config.json: 100%|██████████| 1.24k/1.24k [00:00<00:00, 5.38MB/s] Download complete: 100%|██████████| 1.58G/1.58G [00:04<00:00, 343MB/s] pytorch_model.bin: 0%| | 0.00/1.58G [00:00<?, ?B/s] pytorch_model.bin: 8%|▊ | 134M/1.58G [00:01<00:19, 76.0MB/s] pytorch_model.bin: 76%|███████▌ | 1.21G/1.58G [00:02<00:00, 522MB/s] pytorch_model.bin: 100%|██████████| 1.58G/1.58G [00:02<00:00, 541MB/s] Loading weights: 0%| | 0/170 [00:00<?, ?it/s] Loading weights: 100%|██████████| 170/170 [00:00<00:00, 2742.25it/s] [transformers] ModernBertModel LOAD REPORT from: jhu-clsp/ettin-encoder-400m Key | Status | | ------------------+------------+--+- decoder.weight | UNEXPECTED | | decoder.bias | UNEXPECTED | | head.norm.weight | UNEXPECTED | | head.dense.weight | UNEXPECTED | | Notes: - UNEXPECTED: can be ignored when loading from different task/architecture; not ok if you expect identical arch. Traceback (most recent call last): File "/home/user/app/app.py", line 70, in <module> model = MELDDetector(backbone, hidden_size, config) File "/home/user/app/app.py", line 44, in __init__ nn.Linear(hidden_size, config["num_labels"]), KeyError: 'num_labels' model.safetensors: 0%| | 0.00/1.58G [00:00<?, ?B/s] model.safetensors: 4%|▍ | 67.0M/1.58G [00:01<00:28, 53.4MB/s] model.safetensors: 68%|██████▊ | 1.07G/1.58G [00:02<00:00, 560MB/s]  model.safetensors: 100%|██████████| 1.58G/1.58G [00:02<00:00, 615MB/s]

Container logs: