9 Commits

Author	SHA1	Message	Date
Laurent Mazare	68aa9c7320	Fix the device for the bert attention mask. (#2414)	2024-08-14 10:01:12 +02:00
Zheng Li	4a52aeb437	bert attention mask (#1934) ... * bert attention mask * Allow for using None as a mask. * Revert part of the changes so that the proper default mask applies. * Cosmetic change. * Another cosmetic tweak. --------- Co-authored-by: Laurent <laurent.mazare@gmail.com>	2024-08-01 08:26:19 +02:00
Jani Monoses	63944714f2	Use candle_nn::embedding instead of local copies in a few models. (#1562)	2024-01-10 21:36:27 +01:00
Juarez Bochi	9bd94c1ffa	Speed up bert with approx gelu (#1410)	2023-12-06 17:46:37 +01:00
Laurent Mazare	6975c65112	Share the layer-norm implementation. (#1248)	2023-11-03 06:30:05 +01:00
Laurent Mazare	1704f1b3ae	Consolidate the with-tracing usage. (#1234)	2023-11-01 18:21:36 +00:00
Laurent Mazare	5f20697918	Add the jina-bert embeddings model. (#1187) ... * Add the jina-bert model. * Use alibi. * Remove the unused pragma. * Recompute the alibi embeddings. * Generate the token type ids. * Use the module trait. * Add the jina-bert example. * DType fix. * Get the inference to work.	2023-10-26 16:54:36 +01:00
Laurent Mazare	ce0a4e3a85	Use the gelu-erf activation. (#969)	2023-09-26 22:30:21 +01:00
Laurent Mazare	d3f05eae8c	Move some models to candle-transformers so that it's easier to re-use. (#794) ... * Move some models to candle-transformers so that they can be shared. * Also move falcon. * Move Llama. * Move whisper (partial).	2023-09-10 09:40:27 +01:00