43a007cba4
Upgrading bert example to work with bert-base-uncased.
...
- Always take weights from the hub
- Optional `model_id` + `revision` to use safetensors version
potentially
- Optional loading for `bert-base-uncased` (`weight` vs `gamma`).
- Take the config from the hub.
2023-07-04 14:12:14 +00:00
a57b314780
Add a batch dimension on the bert example.
2023-07-04 06:10:52 +01:00
b6d179cc1c
Allow for batch dimensions in the embedding layer.
2023-07-03 18:37:40 +01:00
9784d1ed9f
Minor tweaks.
2023-07-03 18:31:55 +01:00
5524ca29cc
Remove the fixed length hack.
2023-07-03 17:13:23 +01:00
1ea6690557
Bugfix for transpose.
2023-07-03 17:06:23 +01:00
a7f03a7bb6
Fix the layer norm to properly handle bias.
2023-07-03 16:45:03 +01:00
f379b8feae
Get some embeddings out.
2023-07-03 16:11:16 +01:00
54850e7525
Get the tensors to be loaded properly.
2023-07-03 15:53:31 +01:00
ad52b0377c
Add the varbuilder + check shapes.
2023-07-03 15:32:20 +01:00
f74bddca31
Model creation.
2023-07-03 14:09:46 +01:00
12ac9e1460
Complete (?) the forward pass.
2023-07-03 13:33:32 +01:00
d796945ad8
Add more to the forward pass.
2023-07-03 13:04:41 +01:00
2309c5fac5
Boilerplate code for Bert.
2023-07-03 12:17:06 +01:00
