795 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Adam Treat	6015154bef	Moving everything to subdir for monorepo merge.	2023-05-10 10:26:55 -04:00
AT	bd0250a6f0	Update README.md ... Signed-off-by: AT <manyoso@users.noreply.github.com>	2023-05-10 09:09:29 -04:00
AT	c3062425be	Update README.md ... Signed-off-by: AT <manyoso@users.noreply.github.com>	2023-05-10 09:09:04 -04:00
Adam Treat	0f1d4eaa90	Bump the version to 2.4.2	2023-05-10 09:05:39 -04:00
AT	88a0ee3509	Update issue templates	2023-05-09 23:57:06 -04:00
Adam Treat	14412996e3	Fix some usage events.	2023-05-09 23:43:16 -04:00
Adam Treat	45d7967438	Default to true for compat hardware.	2023-05-09 23:17:36 -04:00
AT	8afae10808	Update README.md	2023-05-09 23:10:53 -04:00
AT	b9669a3f10	Update README.md	2023-05-09 23:10:06 -04:00
AT	dd3e0f8679	Update README.md	2023-05-09 23:04:54 -04:00
Adam Treat	64aff8a35b	Rename to build_and_run.md	2023-05-09 23:02:41 -04:00
AT	b185b9da0d	Update dev_setup.md	2023-05-09 23:00:50 -04:00
AT	cf61b8259f	Update dev_setup.md	2023-05-09 22:36:02 -04:00
AT	daa0801555	Update dev_setup.md	2023-05-09 22:00:42 -04:00
AT	1a40be68fd	Update dev_setup.md	2023-05-09 21:59:11 -04:00
Adam Treat	999ed1b560	Add a page to fill in for setting up a dev environment.	2023-05-09 21:38:24 -04:00
Adam Treat	80bd55590f	Shorten text.	2023-05-09 20:54:16 -04:00
Adam Treat	42926a484f	Couple of bugfixes.	2023-05-09 19:15:18 -04:00
Adam Treat	2206fa7f8c	Provide a user default model setting and honor it.	2023-05-09 17:10:47 -04:00
Adam Treat	069c243f1a	Add MPT info to the download list and fix it so that isDefault will work even if the required version isn't there.	2023-05-09 12:09:49 -04:00
Adam Treat	a13dcfb13b	Move this script and rename.	2023-05-09 11:48:32 -04:00
Adam Treat	9c008fb677	Simplify.	2023-05-09 11:46:33 -04:00
Adam Treat	53a39b9ecf	Don't keep this in memory when it is not needed.	2023-05-08 21:05:50 -04:00
Adam Treat	5f372bd881	Gracefully handle when we have a previous chat where the model that it used has gone away.	2023-05-08 20:51:03 -04:00
Adam Treat	8b80345c98	Copy pasta.	2023-05-08 19:10:22 -04:00
Adam Treat	af4a67c109	Fix for special im_end token in mpt-7b-chat model.	2023-05-08 18:57:40 -04:00
Adam Treat	d3ec333314	Allow these to load for gptj too.	2023-05-08 18:31:20 -04:00
Aaron Miller	5002614b20	mpt: allow q4_2 quantized models to load	2023-05-08 18:23:36 -04:00
Aaron Miller	832720dd27	mpt tokenizer: better special token handling ... closer to the behavior of huggingface `tokenizers`, do not attempt to handle additional tokens as if they were part of the original vocabulary as this cannot prevent them from being split into smaller chunks - handle added tokens *before* the regular tokenizing pass note this is still necessary even with a "proper" tokenizer implementation	2023-05-08 18:23:36 -04:00
Adam Treat	8c4b8f215f	Fix gptj to have lower memory requirements for kv cache and add versioning to the internal state to smoothly handle such a fix in the future.	2023-05-08 17:23:02 -04:00
Adam Treat	ccbd16cf18	Fix the version.	2023-05-08 16:50:21 -04:00
Adam Treat	a549871220	Remove as upstream has removed.	2023-05-08 15:09:23 -04:00
Adam Treat	dfe85386b5	This shouldn't have snuck in.	2023-05-08 15:09:23 -04:00
Adam Treat	992e553cfa	Update to the alibi version that Zach made.	2023-05-08 12:27:01 -04:00
Adam Treat	98aedd2173	Match Helly's impl of kv cache.	2023-05-08 12:21:30 -04:00
Adam Treat	eb77d5157b	Use F16 for kv cache on mpt.	2023-05-08 12:21:30 -04:00
Adam Treat	dc559c1575	Fix for special tokens.	2023-05-08 12:21:30 -04:00
Adam Treat	b6886c0e31	Fix up mpt.	2023-05-08 12:21:30 -04:00
Zach Nussbaum	61e2aabadb	fix: helly changes	2023-05-08 12:21:30 -04:00
Zach Nussbaum	d30be81506	fix: model loading	2023-05-08 12:21:30 -04:00
Zach Nussbaum	f732ba2d56	fix: convert script working	2023-05-08 12:21:30 -04:00
Zach Nussbaum	6a56bcaf06	feat: load model	2023-05-08 12:21:30 -04:00
Zach Nussbaum	58069dc8b9	chore: import for mpt	2023-05-08 12:21:30 -04:00
Zach Nussbaum	03bde18e49	feat: mpt convert from hf to ggml	2023-05-08 12:21:30 -04:00
Zach Nussbaum	2f6ecbe798	feat: build works + tokenizer	2023-05-08 12:21:30 -04:00
Zach Nussbaum	525b703984	feat: add ln 2, rename vars	2023-05-08 12:21:30 -04:00
Zach Nussbaum	aef524b460	feat: mpt wip	2023-05-08 12:21:30 -04:00
Adam Treat	159053be5a	Scaffolding for the mpt <-> ggml project.	2023-05-08 12:21:30 -04:00
Adam Treat	40b976436a	Only generate three words max.	2023-05-08 12:21:30 -04:00
Adam Treat	49a6a6ed65	Restore defaults for repeat penalty too.	2023-05-08 12:21:30 -04:00