feat(initializer): store prefix cache as input_ids tensors

update import block

Edit : add model load method

Edit : add model load method

update initializer.py

fix: use weights_only=True in torch.load to safely load state_dict

Refactor model initialization to use hf_hub_download cache paths

Refactor load_llm: use AutoConfig and direct state_dict loading

Update initializer.py to use explicit Hub filenames

First codes update