Laurent Mazare d32e8199cd Layer norm tweaks (#482) ...

* Add some options to make layer-norm more configurable.

* Add the rms-norm variant.

* Replace the RmsNorm with the shared bits.

2023-08-17 10:07:13 +01:00

..

activation.rs

[nn] Move the Embedding and Activation parts. (#116)

2023-07-10 10:24:52 +01:00

conv.rs

Skeleton for the avg-pool2d and upsample-nearest2d ops. (#337)

2023-08-07 16:15:38 +01:00

embedding.rs

Use index-select for the embeddings as it supports backprop. (#298)

2023-08-01 20:44:43 +01:00

group_norm.rs

Fixes for the stable diffusion example. (#342)

2023-08-08 14:57:09 +01:00

init.rs

Improve the mnist training example. (#276)

2023-07-29 16:28:22 +01:00

layer_norm.rs

Layer norm tweaks (#482)

2023-08-17 10:07:13 +01:00

lib.rs

Layer norm tweaks (#482)

2023-08-17 10:07:13 +01:00

linear.rs

Llama more training (#297)

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

loss.rs

Add the cross-entropy loss. (#287)

2023-07-31 14:26:36 +01:00

ops.rs

Implement group-norm. (#334)

2023-08-07 06:53:05 +01:00

optim.rs

Add the AdamW optimizer. (#307)

2023-08-02 14:03:49 +01:00

var_builder.rs

Expose the varmap inner data. (#411)

2023-08-11 16:58:56 +01:00