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
1,658 Commits 491 Branches 56 Tags 46 MiB
c1dcb3f5b8
Commit Graph

437 Commits

Author SHA1 Message Date
Adam Treat
35f9cdb70a Do not delete saved chats if we fail to serialize properly. 2023-10-11 09:16:02 -04:00
cebtenzzre
9fb135e020
cmake: install the GPT-J plugin (#1487) 2023-10-10 15:50:03 -04:00
Aaron Miller
3c25d81759 make codespell happy 2023-10-10 12:00:06 -04:00
Jan Philipp Harries
4f0cee9330 added EM German Mistral Model 2023-10-10 11:44:43 -04:00
Adam Treat
56c0d2898d Update the language here to avoid misunderstanding. 2023-10-06 14:38:42 -04:00
Adam Treat
b2cd3bdb3f Fix crasher with an empty string for prompt template. 2023-10-06 12:44:53 -04:00
Cebtenzzre
5fe685427a chat: clearer CPU fallback messages 2023-10-06 11:35:14 -04:00
Aaron Miller
9325075f80 fix stray comma in models2.json 
Signed-off-by: Aaron Miller <apage43@ninjawhale.com>
 2023-10-05 18:32:23 -04:00
Adam Treat
f028f67c68 Add starcoder, rift and sbert to our models2.json. 2023-10-05 18:16:19 -04:00
Adam Treat
4528f73479 Reorder and refresh our models2.json. 2023-10-05 18:16:19 -04:00
Cebtenzzre
1534df3e9f backend: do not use Vulkan with non-LLaMA models 2023-10-05 18:16:19 -04:00
Cebtenzzre
672cb850f9 differentiate between init failure and unsupported models 2023-10-05 18:16:19 -04:00
Cebtenzzre
a5b93cf095 more accurate fallback descriptions 2023-10-05 18:16:19 -04:00
Cebtenzzre
75deee9adb chat: make sure to clear fallback reason on success 2023-10-05 18:16:19 -04:00
Cebtenzzre
2eb83b9f2a chat: report reason for fallback to CPU 2023-10-05 18:16:19 -04:00
Adam Treat
ea66669cef Switch to new models2.json for new gguf release and bump our version to 
2.5.0.
 2023-10-05 18:16:19 -04:00
Adam Treat
12f943e966 Fix regenerate button to be deterministic and bump the llama version to latest we have for gguf. 2023-10-05 18:16:19 -04:00
Cebtenzzre
a49a1dcdf4 chatllm: grammar fix 2023-10-05 18:16:19 -04:00
Cebtenzzre
31b20f093a modellist: fix the system prompt 2023-10-05 18:16:19 -04:00
Cebtenzzre
8f3abb37ca fix references to removed model types 2023-10-05 18:16:19 -04:00
Adam Treat
d90d003a1d Latest rebase on llama.cpp with gguf support. 2023-10-05 18:16:19 -04:00
Akarshan Biswas
5f3d739205 appdata: update software description 2023-10-05 10:12:43 -04:00
Akarshan Biswas
b4cf12e1bd Update to 2.4.19 2023-10-05 10:12:43 -04:00
Akarshan Biswas
21a5709b07 Remove unnecessary stuffs from manifest 2023-10-05 10:12:43 -04:00
Akarshan Biswas
4426640f44 Add flatpak manifest 2023-10-05 10:12:43 -04:00
Aaron Miller
6711bddc4c launch browser instead of maintenancetool from offline builds 2023-09-27 11:24:21 -07:00
Aaron Miller
7f979c8258 Build offline installers in CircleCI 2023-09-27 11:24:21 -07:00
Adam Treat
dc80d1e578 Fix up the offline installer. 2023-09-18 16:21:50 -04:00
Adam Treat
f47e698193 Release notes for v2.4.19 and bump the version. 2023-09-16 12:35:08 -04:00
Adam Treat
ecf014f03b Release notes for v2.4.18 and bump the version. 2023-09-16 10:21:50 -04:00
Adam Treat
e6e724d2dc Actually bump the version. 2023-09-16 10:07:20 -04:00
Adam Treat
06a833e652 Send actual and requested device info for those who have opt-in. 2023-09-16 09:42:22 -04:00
Adam Treat
045f6e6cdc Link against ggml in bin so we can get the available devices without loading a model. 2023-09-15 14:45:25 -04:00
Adam Treat
655372dbfa Release notes for v2.4.17 and bump the version. 2023-09-14 17:11:04 -04:00
Adam Treat
aa33419c6e Fallback to CPU more robustly. 2023-09-14 16:53:11 -04:00
Adam Treat
79843c269e Release notes for v2.4.16 and bump the version. 2023-09-14 11:24:25 -04:00
Adam Treat
3076e0bf26 Only show GPU when we're actually using it. 2023-09-14 09:59:19 -04:00
Adam Treat
1fa67a585c Report the actual device we're using. 2023-09-14 08:25:37 -04:00
Adam Treat
21a3244645 Fix a bug where we're not properly falling back to CPU. 2023-09-13 19:30:27 -04:00
Adam Treat
0458c9b4e6 Add version 2.4.15 and bump the version number. 2023-09-13 17:55:50 -04:00
Aaron Miller
6f038c136b init at most one vulkan device, submodule update 
fixes issues w/ multiple of the same gpu
 2023-09-13 12:49:53 -07:00
Adam Treat
86e862df7e Fix up the name and formatting. 2023-09-13 15:48:55 -04:00
Adam Treat
358ff2a477 Show the device we're currently using. 2023-09-13 15:24:33 -04:00
Adam Treat
891ddafc33 When device is Auto (the default) then we will only consider discrete GPU's otherwise fallback to CPU. 2023-09-13 11:59:36 -04:00
Adam Treat
8f99dca70f Bring the vulkan backend to the GUI. 2023-09-13 11:26:10 -04:00
Adam Treat
987546c63b Nomic vulkan backend licensed under the Software for Open Models License (SOM), version 1.0. 2023-08-31 15:29:54 -04:00
Adam Treat
d55cbbee32 Update to newer llama.cpp and disable older forks. 2023-08-31 15:29:54 -04:00
Adam Treat
a63093554f Remove older models that rely upon soon to be no longer supported quantization formats. 2023-08-15 13:19:41 -04:00
Adam Treat
2c0ee50dce Add starcoder 7b. 2023-08-15 09:27:55 -04:00
Victor Tsaran
ca8baa294b
Updated README.md with a wishlist idea (#1315) 
Signed-off-by: Victor Tsaran <vtsaran@yahoo.com>
 2023-08-10 11:27:09 -04:00
Lakshay Kansal
0f2bb506a8
font size changer and updates (#1322) 2023-08-07 13:54:13 -04:00
Akarshan Biswas
c449b71b56
Add LLaMA2 7B model to model.json. (#1296) 
* Add LLaMA2 7B model to model.json.

---------

Signed-off-by: Akarshan Biswas <akarshan.biswas@gmail.com>
 2023-08-02 16:58:14 +02:00
Lakshay Kansal
cbdcde8b75
scrollbar fixed for main chat and chat drawer (#1301) 2023-07-31 12:18:38 -04:00
Lakshay Kansal
3d2db76070
fixed issue of text color changing for code blocks in light mode (#1299) 2023-07-31 12:18:19 -04:00
Aaron Miller
b9e2553995
remove trailing comma from models json (#1284) 2023-07-27 09:14:33 -07:00
Adam Treat
09a143228c New release notes and bump version. 2023-07-27 11:48:16 -04:00
Lakshay Kansal
fc1af4a234 light mode vs dark mode 2023-07-27 09:31:55 -04:00
Adam Treat
6d03b3e500 Add starcoder support. 2023-07-27 09:15:16 -04:00
Adam Treat
397f3ba2d7 Add a little size to the monospace font. 2023-07-27 09:15:16 -04:00
AMOGUS
4974ae917c Update default TopP to 0.4 
TopP 0.1 was found to be somewhat too aggressive, so a more moderate default of 0.4 would be better suited for general use.

Signed-off-by: AMOGUS <137312610+Amogus8P@users.noreply.github.com>
 2023-07-19 10:36:23 -04:00
Lakshay Kansal
6c8669cad3 highlighting rules for html and php and latex 2023-07-14 11:36:01 -04:00
Adam Treat
0efdbfcffe Bert 2023-07-13 14:21:46 -04:00
Adam Treat
315a1f2aa2 Move it back as internal class. 2023-07-13 14:21:46 -04:00
Adam Treat
ae8eb297ac Add sbert backend. 2023-07-13 14:21:46 -04:00
Adam Treat
1f749d7633 Clean up backend code a bit and hide impl. details. 2023-07-13 14:21:46 -04:00
Adam Treat
a0dae86a95 Add bert to models.json 2023-07-13 13:37:12 -04:00
AT
18ca8901f0
Update README.md 
Signed-off-by: AT <manyoso@users.noreply.github.com>
 2023-07-12 16:30:56 -04:00
Adam Treat
e8b19b8e82 Bump version to 2.4.14 and provide release notes. 2023-07-12 14:58:45 -04:00
Adam Treat
8eb0844277 Check if the trimmed version is empty. 2023-07-12 14:31:43 -04:00
Adam Treat
be395c12cc Make all system prompts empty by default if model does not include in training data. 2023-07-12 14:31:43 -04:00
Aaron Miller
6a8fa27c8d Correctly find models in subdirs of model dir 
QDirIterator doesn't seem particular subdir aware, its path() returns
the iterated dir. This was the simplest way I found to get this right.
 2023-07-12 14:18:40 -04:00
Adam Treat
8893db5896 Add wizard model and rename orca to be more specific. 2023-07-12 14:12:46 -04:00
Adam Treat
60627bd41f Prefer 7b models in order of default model load. 2023-07-12 12:50:18 -04:00
Aaron Miller
5df4f1bf8c codespell 2023-07-12 12:49:06 -04:00
Aaron Miller
10ca2c4475 center the spinner 2023-07-12 12:49:06 -04:00
Adam Treat
e9897518d1 Show busy if models.json download taking longer than expected. 2023-07-12 12:49:06 -04:00
Aaron Miller
ad0e7fd01f chatgpt: ensure no extra newline in header 2023-07-12 10:53:25 -04:00
Aaron Miller
f0faa23ad5
cmakelists: always export build commands (#1179) 
friendly for using editors with clangd integration that don't also
manage the build themselves
 2023-07-12 10:49:24 -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
13b2d47be5 Provide an error dialog if for any reason we can't access the settings file. 2023-07-12 08:50:21 -04:00
Adam Treat
e9d42fba35 Don't show first start more than once. 2023-07-11 18:54:53 -04:00
Adam Treat
2679dc1521 Give note about gpt-4 and openai key access. 2023-07-11 15:35:10 -04:00
Adam Treat
806905f747 Explicitly set the color in MyTextField. 2023-07-11 15:27:26 -04:00
Adam Treat
9dccc96e70 Immediately signal when the model is in a new loading state. 2023-07-11 15:10:59 -04:00
Adam Treat
833a56fadd Fix the tap handler on these buttons. 2023-07-11 14:58:54 -04:00
Adam Treat
18dbfddcb3 Fix default thread setting. 2023-07-11 13:07:41 -04:00
Adam Treat
34a3b9c857 Don't block on exit when not connected. 2023-07-11 12:37:21 -04:00
Adam Treat
88bbe30952 Provide a guardrail for OOM errors. 2023-07-11 12:09:33 -04:00
Adam Treat
9ef53163dd Explicitly send the opt out because we were artificially lowering them with settings changes. 2023-07-11 10:53:19 -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
Adam Treat
99cd555743 Provide some guardrails for thread count. 2023-07-10 17:29:51 -04:00
Lakshay Kansal
a190041c6e
json and c# highlighting rules (#1163) 2023-07-10 16:23:32 -04:00
Adam Treat
3e3b05a2a4 Don't process the system prompt when restoring state. 2023-07-10 16:20:19 -04:00
Adam Treat
98dd2ab4bc Provide backup options if models.json does not download synchronously. 2023-07-10 16:14:57 -04:00
Adam Treat
c8d761a004 Add a nicer message. 2023-07-09 15:51:59 -04:00
Adam Treat
e120eb5008 Allow closing the download dialog and display a message to the user if no models are installed. 2023-07-09 15:08:14 -04:00
Adam Treat
fb172a2524 Don't prevent closing the model download dialog. 2023-07-09 14:58:55 -04:00
Adam Treat
15d04a7916 Fix new version dialog ui. 2023-07-09 14:56:54 -04:00
Adam Treat
12083fcdeb When deleting chats we sometimes have to update our modelinfo. 2023-07-09 14:52:08 -04:00
Adam Treat
59f3c093cb Stop generating anything on shutdown. 2023-07-09 14:42:11 -04:00
Adam Treat
e2458454d3 Bump to v2.4.12 and new release notes. 2023-07-09 13:33:07 -04:00
Adam Treat
d9f0245c1b Fix problems with browse of folder in settings dialog. 2023-07-09 13:05:06 -04:00
Adam Treat
58d6f40f50 Fix broken installs. 2023-07-09 11:50:44 -04:00
Adam Treat
85626b3dab Fix model path. 2023-07-09 11:33:58 -04:00
Adam Treat
ee73f1ab1d Shrink the templates. 2023-07-06 17:10:57 -04:00
Akarshan Biswas
c987e56db7 Update CMakeLists.txt - change WaylandClient to WaylandCompositor 
https://doc.qt.io/qt-6/qwaylandcompositor.html

Signed-off-by: Akarshan Biswas <akarshan.biswas@gmail.com>
 2023-07-06 12:50:05 -04:00
Akarshan Biswas
16bd4a14d3 Add Qt6:WaylandClient only to Linux Build 
Signed-off-by: Akarshan Biswas <akarshan.biswas@gmail.com>
 2023-07-06 12:50:05 -04:00
Adam Treat
18316cde39 Bump to 2.4.12 and release notes. 2023-07-06 12:25:25 -04:00
Adam Treat
db528ef1b0 Add a close button for dialogs. 2023-07-06 10:53:56 -04:00
Adam Treat
27981c0d21 Fix broken download/remove/install. 2023-07-05 20:12:37 -04:00
Adam Treat
eab92a9d73 Fix typo and add new show references setting to localdocs. 2023-07-05 19:41:23 -04:00
Adam Treat
0638b45b47 Per model prompts / templates. 2023-07-05 16:30:41 -04:00
Adam Treat
1491c9fe49 Fix build on windows. 2023-07-05 15:51:42 -04:00
Adam Treat
6d9cdf228c Huge change that completely revamps the settings dialog and implements 
per model settings as well as the ability to clone a model into a "character."
This also implements system prompts as well as quite a few bugfixes for
instance this fixes chatgpt.
 2023-07-05 15:51:42 -04:00
Adam Treat
2a6c673c25 Begin redesign of settings dialog. 2023-07-05 15:51:42 -04:00
Adam Treat
dedb0025be Refactor the settings dialog so that it uses a set of components/abstractions 
for all of the tabs and stacks
 2023-07-05 15:51:42 -04:00
Lakshay Kansal
b3c29e4179
implemented support for bash and go highlighting rules (#1138) 
* implemented support for bash and go

* add more commands to bash

* gave precedence to variables over strings in bash
 2023-07-05 11:04:13 -04:00
matthew-gill
fd4081aed8 Update codeblock font 2023-07-05 09:44:25 -04:00
Lakshay Kansal
70cbff70cc created highlighting rules for java using regex for the gpt4all chat interface 2023-06-29 13:11:37 -03:00
Adam Treat
1cd734efdc Provide an abstraction to break up the settings dialog into managable pieces. 2023-06-29 09:59:54 -04:00
Adam Treat
7f252b4970 This completes the work of consolidating all settings that can be changed by the user on new settings object. 2023-06-29 00:44:48 -03:00
Adam Treat
285aa50b60 Consolidate generation and application settings on the new settings object. 2023-06-28 20:36:43 -03:00
Adam Treat
7f66c28649 Use the new settings for response generation. 2023-06-28 20:11:24 -03:00
Adam Treat
a8baa4da52 The sync for save should be after. 2023-06-28 20:11:24 -03:00
Adam Treat
705b480d72 Start moving toward a single authoritative class for all settings. This 
is necessary to get rid of technical debt before we drastically increase
the complexity of settings by adding per model settings and mirostat and
other fun things. Right now the settings are divided between QML and C++
and some convenience methods to deal with settings sync and so on that are
in other singletons. This change consolidates all the logic for settings
into a single class with a single API for both C++ and QML.
 2023-06-28 20:11:24 -03:00
Adam Treat
e70899a26c Make the retrieval/parsing of models.json sync on startup. We were jumping to many hoops to mitigate the async behavior. 2023-06-28 12:32:22 -03:00
Adam Treat
9560336490 Match on the filename too for server mode. 2023-06-28 09:20:05 -04:00
Adam Treat
58cd346686 Bump release again and new release notes. 2023-06-27 18:01:23 -04:00
Adam Treat
0f8f364d76 Fix mac again for falcon. 2023-06-27 17:20:40 -04:00
Adam Treat
8aae4e52b3 Fix for falcon on mac. 2023-06-27 17:13:13 -04:00
Adam Treat
9375c71aa7 New release notes for 2.4.9 and bump version. 2023-06-27 17:01:49 -04:00
Adam Treat
71449bbc4b Fix this correctly? 2023-06-27 16:01:11 -04:00
Adam Treat
07a5405618 Make it clear this is our finetune. 2023-06-27 15:33:38 -04:00
Adam Treat
189ac82277 Fix server mode. 2023-06-27 15:01:16 -04:00
Adam Treat
b56cc61ca2 Don't allow setting an invalid prompt template. 2023-06-27 14:52:44 -04:00
Adam Treat
0780393d00 Don't use local. 2023-06-27 14:13:42 -04:00
Adam Treat
924efd9e25 Add falcon to our models.json 2023-06-27 13:56:16 -04:00
Adam Treat
d3b8234106 Fix spelling. 2023-06-27 14:23:56 -03:00
Adam Treat
42c0a6673a Don't persist the force metal setting. 2023-06-27 14:23:56 -03:00
Adam Treat
267601d670 Enable the force metal setting. 2023-06-27 14:23:56 -03:00
Aaron Miller
e22dd164d8 add falcon to chatllm::serialize 2023-06-27 14:06:39 -03:00
Aaron Miller
198b5e4832 add Falcon 7B model 
Tested with https://huggingface.co/TheBloke/falcon-7b-instruct-GGML/blob/main/falcon7b-instruct.ggmlv3.q4_0.bin
 2023-06-27 14:06:39 -03:00
Adam Treat
985d3bbfa4 Add Orca models to list. 2023-06-27 09:38:43 -04:00
Adam Treat
8558fb4297 Fix models.json for spanning multiple lines with string. 2023-06-26 21:35:56 -04:00
Adam Treat
c24ad02a6a Wait just a bit to set the model name so that we can display the proper name instead of filename. 2023-06-26 21:00:09 -04:00
Adam Treat
57fa8644d6 Make spelling check happy. 2023-06-26 17:56:56 -04:00
Adam Treat
d0a3e82ffc Restore feature I accidentally erased in modellist update. 2023-06-26 17:50:45 -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
Adam Treat
dead954134 Fix save chats setting. 2023-06-26 16:43:37 -04:00