runtime error

Exit code: 1. Reason: model.visual.merger.ln_q.bias | MISSING | model.visual.merger.mlp.2.weight | MISMATCH | Reinit due to size mismatch - ckpt: torch.Size([2048, 5120]) vs model:torch.Size([1280, 5120]) model.visual.merger.mlp.2.bias | MISMATCH | Reinit due to size mismatch - ckpt: torch.Size([2048]) vs model:torch.Size([1280]) Notes: - UNEXPECTED :can be ignored when loading from different task/architecture; not ok if you expect identical arch. - MISSING :those params were newly initialized because missing from the checkpoint. Consider training on your downstream task. - MISMATCH :ckpt weights were loaded, but they did not match the original empty weight shapes. Traceback (most recent call last): File "/app/app.py", line 19, in <module> base_model = Qwen2VLForConditionalGeneration.from_pretrained( BASE_MODEL_ID, torch_dtype=DTYPE, device_map=DEVICE, ) File "/usr/local/lib/python3.13/site-packages/transformers/modeling_utils.py", line 4138, in from_pretrained loading_info = cls._finalize_model_loading(model, load_config, loading_info) File "/usr/local/lib/python3.13/site-packages/transformers/modeling_utils.py", line 4299, in _finalize_model_loading log_state_dict_report( ~~~~~~~~~~~~~~~~~~~~~^ model=model, ^^^^^^^^^^^^ ...<3 lines>... logger=logger, ^^^^^^^^^^^^^^ ) ^ File "/usr/local/lib/python3.13/site-packages/transformers/utils/loading_report.py", line 278, in log_state_dict_report raise RuntimeError( "You set `ignore_mismatched_sizes` to `False`, thus raising an error. For details look at the above report!" ) RuntimeError: You set `ignore_mismatched_sizes` to `False`, thus raising an error. For details look at the above report! Download complete: 100%|██████████| 7.51G/7.51G [00:34<00:00, 220MB/s]

Container logs: