Laurent Mazare ff876c2103 Llama more training (#297) ...

* Rework the var-builder to handle initializations.

* Add some helper functions for layer creation.

* Improve the layer initializations.

* Get initialized variables.

* Precompute the rot embeddings when training lamas.

2023-08-01 19:53:41 +01:00

..

main.rs

Add training for the llama2.c example (#296)

2023-08-01 17:23:07 +01:00

model.rs

Llama more training (#297)

2023-08-01 19:53:41 +01:00

training.rs

Llama more training (#297)

2023-08-01 19:53:41 +01:00

weights.rs

Move the weight bits in a separate module. (#295)

2023-08-01 10:37:06 +01:00