AI/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2024-10-01 01:06:10 -04:00
Code Issues Packages Projects Releases Wiki Activity
286 Commits 491 Branches 56 Tags 46 MiB
c0d4a9d426
Commit Graph

286 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Adam Treat
6256b4fd33 Have to be able to change the download path from the download dialog and other fixes. 2023-04-27 16:27:53 -04:00
Adam Treat
b00da454e4 Provide a description and make the downloader cleaner and prettier. 2023-04-27 14:52:40 -04:00
Adam Treat
62a885de40 Always try and load default model first. Groovy is the default default. 2023-04-27 13:52:29 -04:00
Adam Treat
97baf3d486 Make the input area wrap automatically. 2023-04-27 11:54:53 -04:00
Adam Treat
db3acf9980 Silence warning. 2023-04-27 11:44:41 -04:00
Adam Treat
5a7d40f604 Move the saving of the tokens to the impl and not the callbacks responsibility. 2023-04-27 11:16:51 -04:00
Adam Treat
ba4b28fcd5 Move the promptCallback to own function. 2023-04-27 11:08:15 -04:00
Adam Treat
0e9f85bcda Provide an initial impl. of the C interface. NOTE: has not been tested. 2023-04-27 09:43:24 -04:00
Adam Treat
386ce08fca Track check for updates. 2023-04-27 07:41:23 -04:00
Adam Treat
b19d2f2c21 Add this and unbreak the build. 2023-04-26 22:45:10 -04:00
Aaron Miller
5641c365af download: don't read whole file into ram to md5 it 
we go to the trouble of using a tempfile and then reintroduce
a case of reading the whole file into ram again?
 2023-04-26 22:14:21 -04:00
Aaron Miller
18fa61c025 download: atomically move tempfile when possible 
should save unnecessary time and I/O and eliminate the possibility
of the file being improperly truncated when the temp file is on
the same filesystem as the destination path
 2023-04-26 22:14:21 -04:00
Adam Treat
ee5c58c26c Initial support for opt-in telemetry. 2023-04-26 22:05:56 -04:00
Adam Treat
a3d97fa009 Don't crash when prompt is too large. 2023-04-26 19:08:37 -04:00
Adam Treat
fbce5f2078 Unnecessary after all. 2023-04-26 18:35:53 -04:00
Adam Treat
aadeb47026 Put this before. 2023-04-26 13:54:25 -04:00
Adam Treat
8f913c382c Signing ident. 2023-04-26 13:33:33 -04:00
Adam Treat
7da3bc07cc Update llama.cpp submodule to latest. 2023-04-26 11:50:05 -04:00
Adam Treat
74c611b49a Add back option. 2023-04-26 11:02:05 -04:00
Adam Treat
739ef41325 Add optional. 2023-04-26 09:48:49 -04:00
Adam Treat
0ce8c91240 Allow sha1 2023-04-26 09:44:26 -04:00
Adam Treat
8d421c1ff6 If there is an error, stop the signing process. 2023-04-26 09:22:02 -04:00
Adam Treat
9278265693 Fix the help text. 2023-04-26 09:13:07 -04:00
Adam Treat
c839b19b91 Add first attempt at macOS dmg signing script. 2023-04-26 09:04:45 -04:00
Adam Treat
fd0f92a94e Clean up the docs a bit more still. 2023-04-26 08:22:38 -04:00
Adam Treat
c89096ccb4 Clean up the docs a bit more. 2023-04-26 08:22:38 -04:00
Adam Treat
ac7ecd2cef Clean up the docs a bit. 2023-04-26 08:22:38 -04:00
Adam Treat
832b5d1a96 Only need one opaque pointer. 2023-04-26 08:22:38 -04:00
Adam Treat
102f68b18c Fixup the api a bit. 2023-04-26 08:22:38 -04:00
Adam Treat
3c9139b5d2 Move the backend code into own subdirectory and make it a shared library. Begin fleshing out the C api wrapper that bindings can use. 2023-04-26 08:22:38 -04:00
Adam Treat
d16306a205 Actually fix. 2023-04-25 22:49:23 -04:00
Adam Treat
704ce45a39 Remember to stringify the new response too. 2023-04-25 22:47:01 -04:00
Adam Treat
2e0c9e4e13 Fix problem with datalake ingest when the response contains json forbidden chars that are not properly escaped. 2023-04-25 22:17:44 -04:00
Adam Treat
40c3733b6f Eliminate binding loop. 2023-04-25 21:42:11 -04:00
Adam Treat
73715075c9 Don't display button when no context. 2023-04-25 21:20:56 -04:00
Adam Treat
91e2eab7c3 Spelling. 2023-04-25 16:33:01 -04:00
Adam Treat
b2ba17f6f1 Omit the debug stmt 2023-04-25 16:31:26 -04:00
Aaron Miller
b3e01ae865 settings: remove color hardcode & tab radius, darken border 2023-04-25 16:24:55 -04:00
Aaron Miller
cc6005b18c tab UI fixes 2023-04-25 16:24:55 -04:00
Aaron Miller
b72cf40878 use TextField onEditingFinished instead of onAccepted 
this will save settings on defocus instead of only
on pressing enter

Closes https://github.com/nomic-ai/gpt4all/issues/440
 2023-04-25 16:24:55 -04:00
Aaron Miller
15a979b327 new settings (model path, repeat penalty) w/ tabs 2023-04-25 16:24:55 -04:00
Aaron Miller
cd03c5b7d5 Add QuickDialogs2 to CMake component list 2023-04-25 16:24:55 -04:00
Adam Treat
eac866ee90 A new default prompt template. Seems to work well with the repeat penalty. 2023-04-25 12:37:14 -04:00
Adam Treat
b8b254cd9c Fix the send message only when enter has been pressed or the send icon has been clicked. 2023-04-25 12:13:17 -04:00
Adam Treat
cf8a4dd868 Infinite context window through trimming. 2023-04-25 11:20:51 -04:00
Adam Treat
a79bc4233c Implement repeat penalty for both llama and gptj in gui. 2023-04-25 08:38:29 -04:00
Adam Treat
a02b0c14ca Don't crash right out of the installer ;) 2023-04-24 21:07:16 -04:00
Matthieu Talbot
4cf7e122a9 Fix cli tools instructions 2023-04-24 19:00:15 -04:00
Aaron Miller
29e3e04fcf persistent threadcount setting 
threadcount is now on the Settings object and
gets reapplied after a model switch
 2023-04-24 18:05:08 -04:00
Adam Treat
1b0eac2870 Add debugging code for ssl errors. 2023-04-24 17:52:19 -04:00