13 Commits

Author	SHA1	Message	Date
yzimmermann	4680ef4413	Enable more BERT models (#580) ... * Update convert.py * Update model.py * Update test.py * Update model.py * Update convert.py * Add files via upload * Update convert.py * format * nit * nit --------- Co-authored-by: Awni Hannun <awni@apple.com>	2024-03-19 17:21:33 -07:00
Race	376bb9cc44	bert encoder inherits from nn.Module now (#571)	2024-03-13 10:24:21 -07:00
Angelos Katharopoulos	1fa40067fe	Change tuple type definitions to use Tuple (#308)	2024-01-12 11:15:09 -08:00
Awni Hannun	bbd7172eef	Some fixes / cleanup for BERT example (#269) ... * some fixes/cleaning for bert + test * nit	2024-01-09 08:44:51 -08:00
Awni Hannun	27c0a8c002	Add llms subdir + update README (#145) ... * add llms subdir + update README * nits * use same pre-commit as mlx * update readmes a bit * format	2023-12-20 10:22:25 -08:00
Awni Hannun	9c7e996ff0	Merge pull request #51 from jbarrow/main ... Update BERT to take advantage of bias param in MultiHeadAttention	2023-12-13 15:20:29 -08:00
Joe Barrow	a577abc313	Cleaner masking code	2023-12-09 21:21:24 -05:00
Awni Hannun	5a5decf767	revert accidental change	2023-12-09 14:58:45 -08:00
Awni Hannun	98f4346c81	black format	2023-12-09 14:15:25 -08:00
Joe Barrow	5d4838b02e	Updating BERT model to take advantage of bias param in MultiHeadAttention	2023-12-09 12:07:33 -05:00
Joe Barrow	d873e10dfe	Updating README for current example, making python>=3.8 compatibile, and fixing code type	2023-12-09 12:01:58 -05:00
Joe Barrow	7320456226	Cleaning implementation for merge	2023-12-09 10:41:15 -05:00
Joe Barrow	4e5b8ceafe	BERT implementation	2023-12-08 05:14:11 -05:00