125 Commits

Author	SHA1	Message	Date
laurent	0d99b43792	Line up the textdecoder values with the python implementation.	2023-07-04 12:27:05 +01:00
laurent	aea090401d	Run the text decoding bit.	2023-07-04 12:03:28 +01:00
laurent	a424d95473	Add more of the conv1d op.	2023-07-04 11:15:45 +01:00
laurent	e6b01d0c18	Add the conv1d layer (but not the op).	2023-07-04 10:01:05 +01:00
laurent	d71b31144d	Add a weight extraction script.	2023-07-04 09:29:19 +01:00
laurent	c09aa4b0f4	Add more to the forward pass and fix the cross-attention.	2023-07-04 09:14:28 +01:00
laurent	998cfda9c4	Sinusoid embeddings.	2023-07-04 09:03:25 +01:00
laurent	6728a85676	Add more to the whisper inference.	2023-07-04 08:32:03 +01:00
laurent	512dd9e4d6	Flesh out the whisper example.	2023-07-04 08:01:06 +01:00
laurent	0ca2af6940	Add the residual attention block.	2023-07-04 07:43:36 +01:00
laurent	b1d42231fb	Start sketching the whisper model.	2023-07-04 07:23:02 +01:00
laurent	a57b314780	Add a batch dimension on the bert example.	2023-07-04 06:10:52 +01:00
laurent	b6d179cc1c	Allow for batch dimensions in the embedding layer.	2023-07-03 18:37:40 +01:00
laurent	9784d1ed9f	Minor tweaks.	2023-07-03 18:31:55 +01:00
laurent	5524ca29cc	Remove the fixed length hack.	2023-07-03 17:13:23 +01:00
laurent	1ea6690557	Bugfix for transpose.	2023-07-03 17:06:23 +01:00
laurent	a7f03a7bb6	Fix the layer norm to properly handle bias.	2023-07-03 16:45:03 +01:00
laurent	f379b8feae	Get some embeddings out.	2023-07-03 16:11:16 +01:00
laurent	54850e7525	Get the tensors to be loaded properly.	2023-07-03 15:53:31 +01:00
laurent	ad52b0377c	Add the varbuilder + check shapes.	2023-07-03 15:32:20 +01:00
laurent	f74bddca31	Model creation.	2023-07-03 14:09:46 +01:00
laurent	12ac9e1460	Complete (?) the forward pass.	2023-07-03 13:33:32 +01:00
laurent	d796945ad8	Add more to the forward pass.	2023-07-03 13:04:41 +01:00
laurent	2309c5fac5	Boilerplate code for Bert.	2023-07-03 12:17:06 +01:00
laurent	fdb1acd2ff	Move llama in a cargo-examples directory.	2023-07-03 11:30:58 +01:00