cosmic-snow
fd419caa55
Minor models.json description corrections. ( #1013 )
...
Signed-off-by: cosmic-snow <134004613+cosmic-snow@users.noreply.github.com>
2023-06-18 14:10:29 -04:00
Adam Treat
42e8049564
Bump version and new release notes for metal bugfix edition.
2023-06-16 17:43:10 -04:00
Adam Treat
e2c807d4df
Always install metal on apple.
2023-06-16 17:24:20 -04:00
Adam Treat
d5179ac0c0
Fix cmake build.
2023-06-16 17:18:17 -04:00
Adam Treat
d4283c0053
Fix metal and replit.
2023-06-16 17:13:49 -04:00
Adam Treat
0a0d4a714e
New release and bump the version.
2023-06-16 15:20:23 -04:00
Adam Treat
782e1e77a4
Fix up model names that don't begin with 'ggml-'
2023-06-16 14:43:14 -04:00
Adam Treat
b39a7d4fd9
Fix json.
2023-06-16 14:21:20 -04:00
Adam Treat
6690b49a9f
Converts the following to Q4_0
...
* Snoozy
* Nous Hermes
* Wizard 13b uncensored
Uses the filenames from actual download for these three.
2023-06-16 14:12:56 -04:00
AT
a576220b18
Support loading files if 'ggml' is found anywhere in the name not just at ( #1001 )
...
the beginning and add deprecated flag to models.json so older versions will
show a model, but later versions don't. This will allow us to transition
away from models < ggmlv2 and still allow older installs of gpt4all to work.
2023-06-16 11:09:33 -04:00
Adam Treat
8953b7f6a6
Fix regression in checked of db and network.
2023-06-13 20:08:46 -04:00
Aaron Miller
88616fde7f
llmodel: change tokenToString to not use string_view ( #968 )
...
fixes a definite use-after-free and likely avoids some other
potential ones - std::string will convert to a std::string_view
automatically but as soon as the std::string in question goes out of
scope it is already freed and the string_view is pointing at freed
memory - this is *mostly* fine if its returning a reference to the
tokenizer's internal vocab table but it's, imo, too easy to return a
reference to a dynamically constructed string with this as replit is
doing (and unfortunately needs to do to convert the internal whitespace
replacement symbol back to a space)
2023-06-13 07:14:02 -04:00
Adam Treat
68ff7001ad
Bugfixes for prompt syntax highlighting.
2023-06-12 05:55:14 -07:00
Adam Treat
60d95cdd9b
Fix some bugs with bash syntax and add some C23 keywords.
2023-06-12 05:08:18 -07:00
Adam Treat
e986f18904
Add c++/c highighting support.
2023-06-12 05:08:18 -07:00
Adam Treat
ae46234261
Spelling error.
2023-06-11 14:20:05 -07:00
Adam Treat
318c51c141
Add code blocks and python syntax highlighting.
2023-06-11 14:20:05 -07:00
Adam Treat
b67cba19f0
Don't interfere with selection.
2023-06-11 14:20:05 -07:00
Adam Treat
50c5b82e57
Clean up the context links a bit.
2023-06-11 14:20:05 -07:00
AT
a9c2f47303
Add new solution for context links that does not force regular markdown ( #938 )
...
in responses which is disruptive to code completions in responses.
2023-06-10 10:15:38 -04:00
Aaron Miller
d3ba1295a7
Metal+LLama take two ( #929 )
...
Support latest llama with Metal
---------
Co-authored-by: Adam Treat <adam@nomic.ai>
Co-authored-by: niansa/tuxifan <tuxifan@posteo.de>
2023-06-09 16:48:46 -04:00
Adam Treat
b162b5c64e
Revert "llama on Metal ( #885 )"
...
This reverts commit c55f81b860
.
2023-06-09 15:08:46 -04:00
Aaron Miller
c55f81b860
llama on Metal ( #885 )
...
Support latest llama with Metal
---------
Co-authored-by: Adam Treat <adam@nomic.ai>
Co-authored-by: niansa/tuxifan <tuxifan@posteo.de>
2023-06-09 14:58:12 -04:00
pingpongching
0d0fae0ca8
Change the default values for generation in GUI
2023-06-09 08:51:09 -04:00
Adam Treat
8fb73c2114
Forgot to bump.
2023-06-09 08:45:31 -04:00
Richard Guo
be2310322f
update models json with replit model
2023-06-09 08:44:46 -04:00
Andriy Mulyar
eb26293205
Update CollectionsDialog.qml ( #856 )
...
Phrasing for localdocs
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
2023-06-08 13:44:17 -04:00
Richard Guo
c4706d0c14
Replit Model ( #713 )
...
* porting over replit code model to gpt4all
* replaced memory with kv_self struct
* continuing debug
* welp it built but lot of sus things
* working model loading and somewhat working generate.. need to format response?
* revert back to semi working version
* finally got rid of weird formatting
* figured out problem is with python bindings - this is good to go for testing
* addressing PR feedback
* output refactor
* fixed prompt reponse collection
* cleanup
* addressing PR comments
* building replit backend with new ggmlver code
* chatllm replit and clean python files
* cleanup
* updated replit to match new llmodel api
* match llmodel api and change size_t to Token
* resolve PR comments
* replit model commit comment
2023-06-06 17:09:00 -04:00
Adam Treat
fdffad9efe
New release notes
2023-06-05 14:55:59 -04:00
Adam Treat
f5bdf7c94c
Bump the version.
2023-06-05 14:32:00 -04:00
Andriy Mulyar
d8e821134e
Revert "Fix bug with resetting context with chatgpt model." ( #859 )
...
This reverts commit 031d7149a7
.
2023-06-05 14:25:37 -04:00
Adam Treat
ecfeba2710
Revert "Speculative fix for windows llama models with installer."
...
This reverts commit c99e03e22e
.
2023-06-05 14:25:01 -04:00
Adam Treat
c99e03e22e
Speculative fix for windows llama models with installer.
2023-06-05 13:21:08 -04:00
AT
da757734ea
Release notes for version 2.4.5 ( #853 )
2023-06-05 12:10:17 -04:00
Adam Treat
969ff0ee6b
Fix installers for windows and linux.
2023-06-05 10:50:16 -04:00
Adam Treat
1d4c8e7091
These need to be installed for them to be packaged and work for both mac and windows.
2023-06-05 09:57:00 -04:00
Adam Treat
3a9cc329b1
Fix compile on mac.
2023-06-05 09:31:57 -04:00
Adam Treat
25eec33bda
Try and fix mac.
2023-06-05 09:30:50 -04:00
Adam Treat
91f20becef
Need this so the linux installer packages it as a dependency.
2023-06-05 09:23:43 -04:00
Adam Treat
812b2f4b29
Make installers work with mac/windows for big backend change.
2023-06-05 09:23:17 -04:00
Andriy Mulyar
2e5b114364
Update models.json
...
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
2023-06-04 20:48:45 -04:00
Andriy Mulyar
0db6fd6867
Update models.json ( #838 )
...
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
2023-06-04 20:36:12 -04:00
AT
d5cf584f8d
Remove older models that are not as popular. ( #837 )
...
* Remove older models that are not as popular.
* Update models.json
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
---------
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
Co-authored-by: Andriy Mulyar <andriy.mulyar@gmail.com>
2023-06-04 20:26:43 -04:00
Adam Treat
301d2fdbea
Fix up for newer models on reset context. This fixes the model from totally failing after a reset context.
2023-06-04 19:31:20 -04:00
Adam Treat
bdba2e8de6
Allow for download of models hosted on third party hosts.
2023-06-04 19:02:43 -04:00
Adam Treat
5073630759
Try again with the url.
2023-06-04 18:39:36 -04:00
Adam Treat
6ba37f47c1
Trying out a new feature to download directly from huggingface.
2023-06-04 18:34:04 -04:00
AT
be3c63ffcd
Update build_and_run.md ( #834 )
...
Signed-off-by: AT <manyoso@users.noreply.github.com>
2023-06-04 15:39:32 -04:00
AT
5f95aa9fc6
We no longer have an avx_only repository and better error handling for minimum hardware requirements. ( #833 )
2023-06-04 15:28:58 -04:00
Adam Treat
9f590db98d
Better error handling when the model fails to load.
2023-06-04 14:55:05 -04:00
AT
bbe195ee02
Backend prompt dedup ( #822 )
...
* Deduplicated prompt() function code
2023-06-04 08:59:24 -04:00
Adam Treat
bc624f5389
Add a collection immediately and show a placeholder + busy indicator in localdocs settings.
2023-06-03 10:09:17 -04:00
Adam Treat
55055ca983
Add the ability to change the directory via text field not just 'browse' button.
2023-06-02 22:52:55 -04:00
Adam Treat
25ee51e2ca
Actually use the theme dark color for window background.
2023-06-02 20:19:50 -04:00
Adam Treat
d9ddd373d6
Prevent flashing of white on resize.
2023-06-02 20:16:11 -04:00
Adam Treat
8aba76ad05
Min constraints on about dialog.
2023-06-02 20:05:47 -04:00
Adam Treat
a7f74e9d01
Some tweaks to UI to make window resizing smooth and flow nicely.
2023-06-02 20:00:28 -04:00
niansa/tuxifan
f3564ac6b9
Fixed tons of warnings and clazy findings ( #811 )
2023-06-02 15:46:41 -04:00
niansa/tuxifan
f0be66a221
Fixed spelling error in models.json
...
to make CI happy
Signed-off-by: niansa/tuxifan <tuxifan@posteo.de>
2023-06-02 12:31:09 -04:00
Adam Treat
be9f6ad543
Add models/release.json to github repo to allow PRs
2023-06-02 11:10:00 -04:00
Adam Treat
188770c92a
Remove this as it is no longer useful.
2023-06-02 08:19:18 -04:00
Adam Treat
a41bd6ac0a
Trying to shrink the copy+paste code and do more code sharing between backend model impl.
2023-06-02 07:20:59 -04:00
Adam Treat
031d7149a7
Fix bug with resetting context with chatgpt model.
2023-06-01 17:34:13 -04:00
Adam Treat
94633da2d7
Don't hardcode these.
2023-06-01 17:23:57 -04:00
Adam Treat
28944ac01b
Fix for stale references after we regenerate.
2023-06-01 17:23:57 -04:00
Adam Treat
aea94f756d
Better name for database results.
2023-06-01 17:14:17 -04:00
Adam Treat
f62e439a2d
Make localdocs work with server mode.
2023-06-01 17:14:17 -04:00
Adam Treat
20eff29432
Logger should also output to stderr
2023-06-01 14:15:11 -04:00
Adam Treat
f74363bb3a
Fix compile
2023-06-01 10:58:31 -04:00
niansa/tuxifan
ddb5fa718d
Implemented logging mechanism ( #785 )
2023-06-01 16:50:42 +02:00
niansa
a3d08cdcd5
Dlopen better implementation management (Version 2)
2023-06-01 07:44:15 -04:00
Adam Treat
cae757aacd
Make all the toolbuttons highlight on hover.
2023-05-31 21:07:14 -04:00
Adam Treat
93a05c8834
Fixup the plus new chat button.
2023-05-31 20:42:00 -04:00
Adam Treat
ae51e3f6fa
Use the proper text color for sending messages.
2023-05-31 20:31:59 -04:00
Adam Treat
95244a4d78
Fix warning.
2023-05-31 20:09:05 -04:00
Adam Treat
220e5547db
Draw the indicator for combobox to ensure it looks the same on all platforms.
2023-05-31 19:55:16 -04:00
Adam Treat
1370995b92
Add a custom busy indicator to further align look and feel across platforms.
2023-05-31 19:28:09 -04:00
AT
48275d0dcc
Dlopen backend 5 ( #779 )
...
Major change to the backend that allows for pluggable versions of llama.cpp/ggml. This was squashed merged from dlopen_backend_5 where the history is preserved.
2023-05-31 17:04:01 -04:00
Adam Treat
f4a1f7340c
Fix offset of prompt/response icons for smaller text.
2023-05-31 14:26:59 -04:00
Adam Treat
5f940208e4
Make the comboboxes align in UI.
2023-05-30 21:11:04 -04:00
Adam Treat
64ec93d59b
Some color and theme enhancements to make the UI contrast a bit better.
2023-05-30 21:03:40 -04:00
Adam Treat
e756675d56
Fix wording of this accessible description.
2023-05-30 20:01:12 -04:00
Adam Treat
3e828e1e4b
Add a hover and pressed to the visual indication of MyButton.
2023-05-30 19:58:37 -04:00
Adam Treat
122b14d526
Use the new MyButton for the regenerate response button.
2023-05-30 19:10:38 -04:00
Adam Treat
7aed367c68
Add a label to the model loading visual indicator.
2023-05-30 18:24:26 -04:00
Adam Treat
912cb2a842
Get rid of blocking behavior for regenerate response.
2023-05-30 18:17:59 -04:00
FoivosC
337c7fecac
construct and return the correct reponse when the request is a chat completion
2023-05-30 16:34:23 -04:00
Adam Treat
d9f5626481
Fix remove model from model download for regular models.
2023-05-30 16:16:09 -04:00
Adam Treat
810a3b12cc
This time remember to bump the version right after a release.
2023-05-25 18:26:33 -04:00
Adam Treat
d1ff7132c5
Bump the version number.
2023-05-25 17:08:50 -04:00
Adam Treat
afe3870b7a
Libraries named differently on msvc.
2023-05-25 16:27:09 -04:00
Adam Treat
474c5387f9
Get the backend as well as the client building/working with msvc.
2023-05-25 15:22:45 -04:00
Adam Treat
265488e54a
Add a newline
2023-05-25 11:28:06 -04:00
Adam Treat
98201540a2
Various fixes to remove unnecessary warnings.
2023-05-25 11:28:06 -04:00
Adam Treat
0403a122ca
Don't use the full path in reference text.
2023-05-25 11:28:06 -04:00
Adam Treat
9b0629db8b
Add context link to references.
2023-05-25 11:28:06 -04:00
Adam Treat
db9eecdce4
Store the references separately so they are not sent to datalake.
2023-05-25 11:28:06 -04:00
Adam Treat
b5380c9b7f
Adds the collections to serialize and implement references for localdocs.
2023-05-25 11:28:06 -04:00
Adam Treat
d81302950e
Complete the settings for localdocs.
2023-05-25 11:28:06 -04:00
Adam Treat
01b8c7617f
Add more of the UI for selecting collections for chats.
2023-05-25 11:28:06 -04:00
Adam Treat
2827c5876c
Clean up the settings dialog for localdocs a bit.
2023-05-25 11:28:06 -04:00
Adam Treat
d555ed3b07
Begin implementing the localdocs ui in earnest.
2023-05-25 11:28:06 -04:00
Adam Treat
120fbbf67d
Start fleshing out the localdocs ui.
2023-05-25 11:28:06 -04:00
Adam Treat
af33be7b3e
Add a localdocs tab.
2023-05-25 11:28:06 -04:00
Adam Treat
d9eddbec45
Add a collection list to support a UI.
2023-05-25 11:28:06 -04:00
Adam Treat
68ba9c564b
Specify a large number of suffixes we will search for now.
2023-05-25 11:28:06 -04:00
Adam Treat
c800291e7f
Add prompt processing and localdocs to the busy indicator in UI.
2023-05-25 11:28:06 -04:00
Adam Treat
618895f0a1
Turn off the debugging messages by default.
2023-05-25 11:28:06 -04:00
Adam Treat
c6df4645c8
Add a new muted text color.
2023-05-25 11:28:06 -04:00
Adam Treat
54fc980cb5
Cleanup of the database, better chunking, better matching.
2023-05-25 11:28:06 -04:00
Adam Treat
5f533e76a1
Remove this signal as unnecessary for now.
2023-05-25 11:28:06 -04:00
Adam Treat
e70a1c458b
Add remove folder implementation.
2023-05-25 11:28:06 -04:00
Adam Treat
d88eddbc20
Fixup the rescan. Fix debug output.
2023-05-25 11:28:06 -04:00
Adam Treat
7e42af5f33
localdocs
2023-05-25 11:28:06 -04:00
Adam Treat
b36a520207
Fix the build.
2023-05-23 18:20:17 -04:00
Adam Treat
bcce93555a
Small cleanups for settings dialog.
2023-05-23 14:53:01 -04:00
Justin Wang
5305bce59a
fix typo so padding can be accessed
2023-05-23 13:57:51 -04:00
Justin Wang
d7ab4c0e2d
change accessible description for thumbs up button
2023-05-23 12:15:54 -04:00
Justin Wang
a19ef751dc
add missing accessible props for buttons, remove forgotten duplicate accessible props
2023-05-23 12:15:54 -04:00
Justin Wang
e3d6eb334b
dedup qml: move accessible properties to MyButton
2023-05-23 12:15:54 -04:00
Justin Wang
eb6a7cca47
dedup qml: convert more buttons to MyButton
2023-05-23 11:03:32 -04:00
Adam Treat
8e705d730d
Minor tweaks to look and feel for some dialogs and button.
2023-05-22 22:20:16 -04:00
Justin Wang
2ce22208a3
deduplicate qml: create and use MyCheckBox and MyTextField
2023-05-22 18:03:13 -04:00
Justin Wang
15b3e0d3f6
remove padding
2023-05-22 17:22:05 -04:00
Justin Wang
28b0455451
replace buttons with MyButton
2023-05-22 17:22:05 -04:00
Adam Treat
5c1cf69b8b
Start to deduplicate code in qml.
2023-05-22 14:25:43 -04:00
Adam Treat
cfb45274e0
Fix the tabs so they don't have a double border on the bottom.
2023-05-22 09:04:37 -04:00
Adam Treat
d9698436df
Fix the dialog so it opens on the correct folder.
2023-05-22 09:04:25 -04:00
Juuso Alasuutari
81fdc28e58
llmodel: constify LLModel::threadCount()
2023-05-22 08:54:46 -04:00
Andriy Mulyar
914519e772
Update build_and_run.md ( #636 )
...
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
2023-05-18 21:40:17 -04:00
Shukri
bce2b3025b
Fix typo in README
2023-05-17 09:56:20 -04:00
Adam Treat
a86a1aea6b
Fix for windows/mac installers.
2023-05-16 13:06:42 -04:00
Adam Treat
7221169eff
Remove davinci-003 option.
2023-05-16 13:06:42 -04:00
Adam Treat
86b6d40d08
Bump the version.
2023-05-16 13:06:42 -04:00
Yaroslav Halchenko
e4bc9c0c3b
fix ambigous typo
2023-05-16 11:33:59 -04:00
Adam Treat
79d6243fe1
Use the default for max_tokens to avoid errors.
2023-05-16 10:31:55 -04:00
Adam Treat
b24ace372b
Add ability to remove models.
2023-05-16 10:31:55 -04:00
Adam Treat
47059ad9f1
Send the prompt template with conversations to the datalake.
2023-05-16 10:31:55 -04:00
Adam Treat
748e7977ca
Generate the new prompt/response pair before model loading in server mode.
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
0cd509d530
Add large network icon background for chatgpt and server modes.
2023-05-16 10:31:55 -04:00
Adam Treat
dd27c10f54
Preliminary support for chatgpt models.
2023-05-16 10:31:55 -04:00
Adam Treat
da3828af89
Use compact json format.
2023-05-16 10:31:55 -04:00
Adam Treat
b71c0ac3bd
The server has different lifetime mgmt than the other chats.
2023-05-13 19:34:54 -04:00
Adam Treat
ddc24acf33
Much better memory mgmt for multi-threaded model loading/unloading.
2023-05-13 19:10:56 -04:00
Adam Treat
2989b74d43
httpserver
2023-05-13 19:07:06 -04:00
Adam Treat
76675536b0
Cleanup the chatllm properly.
2023-05-12 17:11:52 -04:00
Adam Treat
4a2e3e55ae
Fix typo.
2023-05-11 16:48:20 -04:00
AT
2c5e2bf1ee
Update README.md
2023-05-11 15:31:01 -04:00
AT
507a96b2f3
Update README.md
2023-05-10 12:10:33 -04:00