21 Commits

Author	SHA1	Message	Date
somebody	3928d86339	Fall back to unpatched HF	2023-07-08 14:36:45 -05:00
somebody	fd6f66a98d	Patch _rebuild_from_type_v2 to not try converting LazyTensors to Tensors	2023-07-08 13:57:05 -05:00
somebody	802929f5f2	Patch safetensors again	2023-07-07 14:54:40 -05:00
somebody	35f3687667	Merge branch 'united' of https://github.com/henk717/KoboldAI into accelerate-offloading	2023-07-07 14:54:12 -05:00
somebody	cfe1f5b514	Stub seek_offset for cache sorting in load loop ... The way Safetensors individual weight loading is implemented doesn't take full advantage of the cache ordering system thing, so this can just be left at zero for now.	2023-07-07 14:49:46 -05:00
Henk	76d21bb142	Universal ziproot for lazy_loader	2023-07-07 13:37:32 +02:00
somebody	6b83944e9b	Use VE's patched load_from_state_dict on TPU for loading empty weights	2023-07-05 18:36:57 -05:00
somebody	7f869a54d8	Just use accelerate on tpu	2023-07-03 17:18:48 -05:00
somebody	31a3046a18	Load empty modules without accelerate	2023-07-03 17:07:18 -05:00
somebody	c56214c275	Fix loading bar	2023-06-21 16:27:22 -05:00
somebody	ceaefa9f5e	Not quite	2023-05-28 14:57:45 -05:00
somebody	ed0728188a	More cleaning	2023-05-28 13:22:32 -05:00
somebody	14241fc156	Speed	2023-05-28 13:03:24 -05:00
somebody	6f93150e4d	Work on lazyload	2023-05-28 12:25:31 -05:00
somebody	1546b9efaa	Hello its breaking breakmodel time	2023-05-27 16:31:53 -05:00
Henk	59c96b5b7a	Unban fix	2023-05-15 22:38:12 +02:00
Henk	c5100b4eab	Unban Tensor	2023-05-15 22:21:22 +02:00
Henk	56443bc7ea	Unban torch._tensor._rebuild_tensor_v2	2023-05-15 21:44:01 +02:00
onesome	1db9d9ba61	Lazyload: Whoops	2023-04-25 18:46:54 -05:00
onesome	e28e268a2d	Use safetensors only when available	2023-04-25 18:32:37 -05:00
somebody	9d70646e4d	Lazyload: Safetensors	2023-04-02 15:40:34 -05:00