Torch not compiled with cuda enabled #2
Description
i am on a macbook air m1. installed pytorch from https://developer.apple.com/metal/pytorch/. pytorch installed successfully but when i run main.py i get the output:
[INFO] Initializing SearchSession for query_id=a973ad1e
model.safetensors.index.json: 100%|███████████████| 65.1k/65.1k [00:00<00:00, 70.1MB/s]
model-00001-of-00002.safetensors: 100%|███████████| 4.99G/4.99G [01:58<00:00, 42.2MB/s]
model-00002-of-00002.safetensors: 100%|█████████████| 862M/862M [00:20<00:00, 42.3MB/s]
Downloading shards: 100%|████████████████████████████████| 2/2 [02:19<00:00, 69.60s/it]
Loading checkpoint shards: 0%| | 0/2 [00:00<?, ?it/s]
Traceback (most recent call last):
File "/Users/danielmoss/NanoSage/main.py", line 54, in
main()
File "/Users/danielmoss/NanoSage/main.py", line 32, in main
session = SearchSession(
^^^^^^^^^^^^^^
File "/Users/danielmoss/NanoSage/search_session.py", line 174, in init
self.model, self.processor, self.model_type = load_retrieval_model(
^^^^^^^^^^^^^^^^^^^^^
File "/Users/danielmoss/NanoSage/knowledge_base.py", line 16, in load_retrieval_model
model = ColPaliForRetrieval.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/lib/python3.11/site-packages/transformers/modeling_utils.py", line 4245, in from_pretrained
) = cls._load_pretrained_model(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/lib/python3.11/site-packages/transformers/modeling_utils.py", line 4815, in _load_pretrained_model
new_error_msgs, offload_index, state_dict_index = _load_state_dict_into_meta_model(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/lib/python3.11/site-packages/transformers/modeling_utils.py", line 873, in _load_state_dict_into_meta_model
set_module_tensor_to_device(model, param_name, param_device, **set_module_kwargs)
File "/opt/anaconda3/lib/python3.11/site-packages/accelerate/utils/modeling.py", line 330, in set_module_tensor_to_device
new_value = value.to(device)
^^^^^^^^^^^^^^^^
File "/opt/anaconda3/lib/python3.11/site-packages/torch/cuda/init.py", line 310, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
How can i enable cuda since it says its not working?