Commit Graph

364 Commits

Author SHA1 Message Date
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
Adam Treat
c054efa6ac Send info on how many are running into this error. 2023-05-08 08:31:35 -04:00
Adam Treat
6d943917f1 Fail early/gracefully if incompatible hardware detected. And default to universal builds on mac. 2023-05-08 08:23:00 -04:00
Adam Treat
3c30310539 Convert the old format properly. 2023-05-08 05:53:16 -04:00
Adam Treat
7b66cb7119 Add debug for chatllm model loading and fix order of getting rid of the
dummy chat when no models are restored.
2023-05-07 14:40:02 -04:00
Adam Treat
9bd5609ba0 Deserialize one at a time and don't block gui until all of them are done. 2023-05-07 09:20:09 -04:00
Adam Treat
86da175e1c Use last lts for this. 2023-05-07 06:39:32 -04:00
Adam Treat
ab13148430 The GUI should come up immediately and not wait on deserializing from disk. 2023-05-06 20:01:14 -04:00
Adam Treat
eb7b61a76d Move the location of the chat files to the model download directory and add a magic+version. 2023-05-06 18:51:49 -04:00
Aaron Miller
7a8f437f8f add name to LICENSE 2023-05-06 13:11:39 -04:00
Adam Treat
e397fda250 Bump the version and save up to an order of magnitude of disk space for chat files. 2023-05-05 20:12:00 -04:00
Adam Treat
8d2c8c8cb0 Turn off saving chats to disk by default as it eats so much disk space. 2023-05-05 12:30:11 -04:00