Aratako/DeepSeek-R1-Distill-Qwen-32B-bnb-4bit · No longer working when building

This seems to no longer be working in HF Space this morning. I duplicated the space and there is an error, probably from some upstream dependency changing:

Traceback (most recent call last): File "/home/user/app/app.py", line 50, in model = AutoModelForCausalLM.from_pretrained("unsloth/DeepSeek-R1-Distill-Qwen-32B-bnb-4bit", device_map="auto") # to("cuda:0") File "/usr/local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 564, in from_pretrained return model_class.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4224, in from_pretrained ) = cls._load_pretrained_model( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4794, in loadpretrained_model new_error_msgs, offload_index, state_dict_index = loadstate_dict_into_meta_model( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 873, in loadstate_dict_into_meta_model set_module_tensor_to_device(model, param_name, param_device, **set_module_kwargs) File "/usr/local/lib/python3.10/site-packages/accelerate/utils/modeling.py", line 287, in set_module_tensor_to_device raise ValueError( ValueError: Trying to set a tensor of shape (70778880, 1) in "weight" (which has shape (5120, 27648)), this looks incorrect.