12 Commits

Author	SHA1	Message	Date
Jared Van Bortel	061d1969f8	expose n_gpu_layers parameter of llama.cpp (#1890) ... Also dynamically limit the GPU layers and context length fields to the maximum supported by the model. Signed-off-by: Jared Van Bortel <jared@nomic.ai>	2024-01-31 14:17:44 -05:00
Jared Van Bortel	d1c56b8b28	Implement configurable context length (#1749)	2023-12-16 17:58:15 -05:00
Aaron Miller	ad0e7fd01f	chatgpt: ensure no extra newline in header	2023-07-12 10:53:25 -04:00
Adam Treat	0d726b22b8	When we explicitly cancel an operation we shouldn't throw an error.	2023-07-12 10:34:10 -04:00
Adam Treat	34a3b9c857	Don't block on exit when not connected.	2023-07-11 12:37:21 -04:00
Adam Treat	4f9e489093	Don't use a local event loop which can lead to recursion and crashes.	2023-07-11 10:08:03 -04:00
Adam Treat	8467e69f24	Check that we're not null. This is necessary because the loop can make us recursive. Need to fix that.	2023-07-10 17:30:08 -04:00
Aaron Miller	b19a3e5b2c	add requiredMem method to llmodel impls ... most of these can just shortcut out of the model loading logic llama is a bit worse to deal with because we submodule it so I have to at least parse the hparams, and then I just use the size on disk as an estimate for the mem size (which seems reasonable since we mmap() the llama files anyway)	2023-06-26 18:27:58 -03:00
Juuso Alasuutari	81fdc28e58	llmodel: constify LLModel::threadCount()	2023-05-22 08:54:46 -04:00
Adam Treat	79d6243fe1	Use the default for max_tokens to avoid errors.	2023-05-16 10:31:55 -04:00
Adam Treat	f931de21c5	Add save/restore to chatgpt chats and allow serialize/deseralize from disk.	2023-05-16 10:31:55 -04:00
Adam Treat	dd27c10f54	Preliminary support for chatgpt models.	2023-05-16 10:31:55 -04:00