4 Commits

Author	SHA1	Message	Date
laurent	60a5598c8b	Fix some shape errors.	2023-06-25 17:56:59 +01:00
laurent	817e4b5005	Rework the embeddings so that it works on non-contiguous weights + factor out some code.	2023-06-25 17:37:47 +01:00
laurent	334524e2c4	Take as input slices of tensors as well as slices of &Tensors.	2023-06-25 17:07:09 +01:00
laurent	90c140ff4b	Start sketching the llama example.	2023-06-25 13:51:20 +01:00