37 Commits

Author	SHA1	Message	Date
Goekdeniz-Guelmez	2ed51946ab	still gibberish	2024-12-27 15:36:37 +01:00
Goekdeniz-Guelmez	f4cbe27b0f	new set but still gibberish	2024-12-27 15:27:09 +01:00
Goekdeniz-Guelmez	d044db959d	update	2024-12-27 15:17:45 +01:00
Goekdeniz-Guelmez	0ae536c423	update: using einsum on som elines making it faster, but still generates Gibberish on Codestral	2024-12-18 19:32:22 +01:00
Goekdeniz-Guelmez	dff4e52910	adding the modelnames in the LORA.md file and removing unused functions from mamba2.py	2024-12-12 22:52:00 +01:00
Goekdeniz-Guelmez	a883e39f41	optimizing the code for faster inference but still generates giberish	2024-12-12 21:08:33 +01:00
Goekdeniz-Guelmez	184d3d3267	clean up	2024-12-10 18:20:13 +01:00
Goekdeniz-Guelmez	80e88b4f4d	nits	2024-12-10 18:18:59 +01:00
Goekdeniz-Guelmez	b10afe3662	nits	2024-12-10 18:15:12 +01:00
Goekdeniz-Guelmez	9f8a6a3509	inference on codestral works but is giberish	2024-12-10 17:34:44 +01:00
Goekdeniz-Guelmez	38e5801edb	loading codestral works but no tinference	2024-11-24 16:26:45 +01:00
Goekdeniz-Guelmez	57b1717cf5	inference fixed	2024-11-21 22:25:58 +01:00
Goekdeniz-Guelmez	e22b2dbf27	Fixed streaming generation and got rid of generating gibberish, but is still a litle slow: 0.222 tokens-per-sec	2024-11-21 22:01:28 +01:00
Goekdeniz-Guelmez	1d851069ea	nits	2024-11-10 17:21:18 +01:00
Goekdeniz-Guelmez	1a6688384d	imopemented multi Token inputs, but still generating Gibberish	2024-11-10 17:19:00 +01:00
Goekdeniz-Guelmez	2f95b361a8	removed the custom Mamba2Cache adn updated the existing MambaCache but still only one input Token and outputs gibberish	2024-11-10 16:57:03 +01:00
Goekdeniz-Guelmez	3a499f9735	fixed inference slowness but it cant handle multible Token inputs and is generateing gibberish	2024-11-10 16:35:07 +01:00
Goekdeniz-Guelmez	800b60239c	save checkpoint	2024-11-10 14:36:26 +01:00
Goekdeniz-Guelmez	906f972d36	save push	2024-11-06 16:35:46 +01:00
Goekdeniz-Guelmez	58b448dc0b	updates	2024-10-30 21:23:13 +01:00
Goekdeniz-Guelmez	7c8849e795	update	2024-10-24 16:16:42 +02:00
Goekdeniz-Guelmez	a677638c4b	inference works but is hella slow	2024-10-22 23:06:06 +02:00
Goekdeniz-Guelmez	9ab581d678	notes	2024-10-22 22:10:53 +02:00
Goekdeniz-Guelmez	e43a2ab229	not working, incorrect handling with cache probably	2024-10-22 22:04:25 +02:00
Goekdeniz-Guelmez	55485b98e8	update	2024-10-22 21:23:47 +02:00
Goekdeniz-Guelmez	758597eaa8	adding multi token input and correct cache handling in ssm step	2024-10-22 20:44:23 +02:00
Goekdeniz-Guelmez	b9c57cd429	generation works! trying training now	2024-10-22 18:25:59 +02:00
Goekdeniz-Guelmez	c1634ce81b	still generating gibberish	2024-10-20 18:41:28 +02:00
Goekdeniz-Guelmez	ab4cf1d1cf	generation works but outputs gibberish	2024-10-20 18:04:34 +02:00
Goekdeniz-Guelmez	4ab5139c05	quick save	2024-10-20 16:11:39 +02:00
Goekdeniz-Guelmez	cd036ccfb5	fix generation works too (almost)	2024-10-16 21:13:36 +02:00
Goekdeniz-Guelmez	8073cb486c	adding debug statements (somehiw generating only goes through the fist MambaMixer block pass)	2024-10-16 21:09:30 +02:00
Goekdeniz-Guelmez	00ba27fe6c	adding debug statements	2024-10-11 21:36:41 +02:00
Goekdeniz-Guelmez	6f88dd59d7	quick clean up and fix	2024-10-11 21:08:13 +02:00
Goekdeniz-Guelmez	4e1236cbf6	fixing loading the model	2024-10-11 20:53:29 +02:00
Goekdeniz-Guelmez	264ba43707	update trainer/lora.py and adding DepthWiseConv1d because mlx 0.18.0 doesnt axepts groups parameter	2024-10-02 19:19:32 +02:00
Gökdeniz Gülmez	49b9fc1a4c	Create mamba2.py	2024-10-02 12:48:15 +02:00