17 Commits

Author	SHA1	Message	Date
Awni Hannun	9063f1a1e3	fix use for llama 2 from meta (#144)	2023-12-18 19:33:17 -08:00
Awni Hannun	e709b846ff	32 GB example	2023-12-15 12:20:15 -08:00
Awni Hannun	24a6de2acb	32 GB example	2023-12-15 12:18:29 -08:00
Awni Hannun	f019d836ee	keep base weights in fp16	2023-12-15 10:42:18 -08:00
Awni Hannun	6dc067d30c	use lower precision base weights	2023-12-15 10:29:42 -08:00
Awni Hannun	4444c7a4a5	more nits	2023-12-15 10:06:14 -08:00
Awni Hannun	c889e09773	fix readme	2023-12-15 09:59:07 -08:00
Awni Hannun	9550e1de17	custom data with lora	2023-12-15 09:56:10 -08:00
Daniel Strobusch	ba4cb95d8e	fix "request access" form url for Llama models	2023-12-13 10:19:29 +01:00
Awni Hannun	cba703d1f1	fix conversion	2023-12-10 16:56:41 -08:00
Awni Hannun	00e21705c2	few more nits	2023-12-09 14:20:19 -08:00
Awni Hannun	dfe79a46f2	black format	2023-12-09 14:15:25 -08:00
Awni Hannun	8094503a68	generalize lora finetuning for llama and mistral	2023-12-09 14:13:55 -08:00
张嘉豪	eab568b391	fix: Unsupported BFloat16 Data Type Issue with MPS Backend	2023-12-08 16:19:35 +08:00
waterstone	2b08a25557	Update README.md	2023-12-07 16:44:29 +08:00
Awni Hannun	5c6bdeb621	add copyright in source	2023-11-30 11:08:53 -08:00
Awni Hannun	bbb69d8d36	lora	2023-11-29 14:14:11 -08:00