├── LICENSE ├── MoD_sampling.ipynb ├── MoD_training.ipynb ├── README.md └── mixture_of_depths ├── __init__.py ├── generation.py ├── inference.py ├── routing_transformer.py └── train.py /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sramshetty/mixture-of-depths/HEAD/LICENSE -------------------------------------------------------------------------------- /MoD_sampling.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sramshetty/mixture-of-depths/HEAD/MoD_sampling.ipynb -------------------------------------------------------------------------------- /MoD_training.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sramshetty/mixture-of-depths/HEAD/MoD_training.ipynb -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sramshetty/mixture-of-depths/HEAD/README.md -------------------------------------------------------------------------------- /mixture_of_depths/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /mixture_of_depths/generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sramshetty/mixture-of-depths/HEAD/mixture_of_depths/generation.py -------------------------------------------------------------------------------- /mixture_of_depths/inference.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sramshetty/mixture-of-depths/HEAD/mixture_of_depths/inference.py -------------------------------------------------------------------------------- /mixture_of_depths/routing_transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sramshetty/mixture-of-depths/HEAD/mixture_of_depths/routing_transformer.py -------------------------------------------------------------------------------- /mixture_of_depths/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/sramshetty/mixture-of-depths/HEAD/mixture_of_depths/train.py --------------------------------------------------------------------------------