cebtenzzre
9fb135e020
cmake: install the GPT-J plugin ( #1487 )
8 months ago
Aaron Miller
3c25d81759
make codespell happy
8 months ago
Jan Philipp Harries
4f0cee9330
added EM German Mistral Model
8 months ago
Adam Treat
56c0d2898d
Update the language here to avoid misunderstanding.
8 months ago
Adam Treat
b2cd3bdb3f
Fix crasher with an empty string for prompt template.
8 months ago
Cebtenzzre
5fe685427a
chat: clearer CPU fallback messages
8 months ago
Aaron Miller
9325075f80
fix stray comma in models2.json
...
Signed-off-by: Aaron Miller <apage43@ninjawhale.com>
8 months ago
Adam Treat
f028f67c68
Add starcoder, rift and sbert to our models2.json.
8 months ago
Adam Treat
4528f73479
Reorder and refresh our models2.json.
8 months ago
Cebtenzzre
1534df3e9f
backend: do not use Vulkan with non-LLaMA models
8 months ago
Cebtenzzre
672cb850f9
differentiate between init failure and unsupported models
8 months ago
Cebtenzzre
a5b93cf095
more accurate fallback descriptions
8 months ago
Cebtenzzre
75deee9adb
chat: make sure to clear fallback reason on success
8 months ago
Cebtenzzre
2eb83b9f2a
chat: report reason for fallback to CPU
8 months ago
Adam Treat
ea66669cef
Switch to new models2.json for new gguf release and bump our version to
...
2.5.0.
8 months ago
Adam Treat
12f943e966
Fix regenerate button to be deterministic and bump the llama version to latest we have for gguf.
8 months ago
Cebtenzzre
a49a1dcdf4
chatllm: grammar fix
8 months ago
Cebtenzzre
31b20f093a
modellist: fix the system prompt
8 months ago
Cebtenzzre
8f3abb37ca
fix references to removed model types
8 months ago
Adam Treat
d90d003a1d
Latest rebase on llama.cpp with gguf support.
8 months ago
Akarshan Biswas
5f3d739205
appdata: update software description
8 months ago
Akarshan Biswas
b4cf12e1bd
Update to 2.4.19
8 months ago
Akarshan Biswas
21a5709b07
Remove unnecessary stuffs from manifest
8 months ago
Akarshan Biswas
4426640f44
Add flatpak manifest
8 months ago
Aaron Miller
6711bddc4c
launch browser instead of maintenancetool from offline builds
8 months ago
Aaron Miller
7f979c8258
Build offline installers in CircleCI
8 months ago
Adam Treat
dc80d1e578
Fix up the offline installer.
9 months ago
Adam Treat
f47e698193
Release notes for v2.4.19 and bump the version.
9 months ago
Adam Treat
ecf014f03b
Release notes for v2.4.18 and bump the version.
9 months ago
Adam Treat
e6e724d2dc
Actually bump the version.
9 months ago
Adam Treat
06a833e652
Send actual and requested device info for those who have opt-in.
9 months ago
Adam Treat
045f6e6cdc
Link against ggml in bin so we can get the available devices without loading a model.
9 months ago
Adam Treat
655372dbfa
Release notes for v2.4.17 and bump the version.
9 months ago
Adam Treat
aa33419c6e
Fallback to CPU more robustly.
9 months ago
Adam Treat
79843c269e
Release notes for v2.4.16 and bump the version.
9 months ago
Adam Treat
3076e0bf26
Only show GPU when we're actually using it.
9 months ago
Adam Treat
1fa67a585c
Report the actual device we're using.
9 months ago
Adam Treat
21a3244645
Fix a bug where we're not properly falling back to CPU.
9 months ago
Adam Treat
0458c9b4e6
Add version 2.4.15 and bump the version number.
9 months ago
Aaron Miller
6f038c136b
init at most one vulkan device, submodule update
...
fixes issues w/ multiple of the same gpu
9 months ago
Adam Treat
86e862df7e
Fix up the name and formatting.
9 months ago
Adam Treat
358ff2a477
Show the device we're currently using.
9 months ago
Adam Treat
891ddafc33
When device is Auto (the default) then we will only consider discrete GPU's otherwise fallback to CPU.
9 months ago
Adam Treat
8f99dca70f
Bring the vulkan backend to the GUI.
9 months ago
Adam Treat
987546c63b
Nomic vulkan backend licensed under the Software for Open Models License (SOM), version 1.0.
9 months ago
Adam Treat
d55cbbee32
Update to newer llama.cpp and disable older forks.
9 months ago
Adam Treat
a63093554f
Remove older models that rely upon soon to be no longer supported quantization formats.
10 months ago
Adam Treat
2c0ee50dce
Add starcoder 7b.
10 months ago
Victor Tsaran
ca8baa294b
Updated README.md with a wishlist idea ( #1315 )
...
Signed-off-by: Victor Tsaran <vtsaran@yahoo.com>
10 months ago
Lakshay Kansal
0f2bb506a8
font size changer and updates ( #1322 )
10 months ago
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>
10 months ago
Lakshay Kansal
cbdcde8b75
scrollbar fixed for main chat and chat drawer ( #1301 )
10 months ago
Lakshay Kansal
3d2db76070
fixed issue of text color changing for code blocks in light mode ( #1299 )
10 months ago
Aaron Miller
b9e2553995
remove trailing comma from models json ( #1284 )
10 months ago
Adam Treat
09a143228c
New release notes and bump version.
10 months ago
Lakshay Kansal
fc1af4a234
light mode vs dark mode
10 months ago
Adam Treat
6d03b3e500
Add starcoder support.
10 months ago
Adam Treat
397f3ba2d7
Add a little size to the monospace font.
10 months ago
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>
11 months ago
Lakshay Kansal
6c8669cad3
highlighting rules for html and php and latex
11 months ago
Adam Treat
0efdbfcffe
Bert
11 months ago
Adam Treat
315a1f2aa2
Move it back as internal class.
11 months ago
Adam Treat
ae8eb297ac
Add sbert backend.
11 months ago
Adam Treat
1f749d7633
Clean up backend code a bit and hide impl. details.
11 months ago
Adam Treat
a0dae86a95
Add bert to models.json
11 months ago
AT
18ca8901f0
Update README.md
...
Signed-off-by: AT <manyoso@users.noreply.github.com>
11 months ago
Adam Treat
e8b19b8e82
Bump version to 2.4.14 and provide release notes.
11 months ago
Adam Treat
8eb0844277
Check if the trimmed version is empty.
11 months ago
Adam Treat
be395c12cc
Make all system prompts empty by default if model does not include in training data.
11 months ago
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.
11 months ago
Adam Treat
8893db5896
Add wizard model and rename orca to be more specific.
11 months ago
Adam Treat
60627bd41f
Prefer 7b models in order of default model load.
11 months ago
Aaron Miller
5df4f1bf8c
codespell
11 months ago
Aaron Miller
10ca2c4475
center the spinner
11 months ago
Adam Treat
e9897518d1
Show busy if models.json download taking longer than expected.
11 months ago
Aaron Miller
ad0e7fd01f
chatgpt: ensure no extra newline in header
11 months ago
Aaron Miller
f0faa23ad5
cmakelists: always export build commands ( #1179 )
...
friendly for using editors with clangd integration that don't also
manage the build themselves
11 months ago
Adam Treat
0d726b22b8
When we explicitly cancel an operation we shouldn't throw an error.
11 months ago
Adam Treat
13b2d47be5
Provide an error dialog if for any reason we can't access the settings file.
11 months ago
Adam Treat
e9d42fba35
Don't show first start more than once.
11 months ago
Adam Treat
2679dc1521
Give note about gpt-4 and openai key access.
11 months ago
Adam Treat
806905f747
Explicitly set the color in MyTextField.
11 months ago
Adam Treat
9dccc96e70
Immediately signal when the model is in a new loading state.
11 months ago
Adam Treat
833a56fadd
Fix the tap handler on these buttons.
11 months ago
Adam Treat
18dbfddcb3
Fix default thread setting.
11 months ago
Adam Treat
34a3b9c857
Don't block on exit when not connected.
11 months ago
Adam Treat
88bbe30952
Provide a guardrail for OOM errors.
11 months ago
Adam Treat
9ef53163dd
Explicitly send the opt out because we were artificially lowering them with settings changes.
11 months ago
Adam Treat
4f9e489093
Don't use a local event loop which can lead to recursion and crashes.
11 months ago
Adam Treat
8467e69f24
Check that we're not null. This is necessary because the loop can make us recursive. Need to fix that.
11 months ago
Adam Treat
99cd555743
Provide some guardrails for thread count.
11 months ago
Lakshay Kansal
a190041c6e
json and c# highlighting rules ( #1163 )
11 months ago
Adam Treat
3e3b05a2a4
Don't process the system prompt when restoring state.
11 months ago
Adam Treat
98dd2ab4bc
Provide backup options if models.json does not download synchronously.
11 months ago
Adam Treat
c8d761a004
Add a nicer message.
11 months ago
Adam Treat
e120eb5008
Allow closing the download dialog and display a message to the user if no models are installed.
11 months ago
Adam Treat
fb172a2524
Don't prevent closing the model download dialog.
11 months ago
Adam Treat
15d04a7916
Fix new version dialog ui.
11 months ago
Adam Treat
12083fcdeb
When deleting chats we sometimes have to update our modelinfo.
11 months ago
Adam Treat
59f3c093cb
Stop generating anything on shutdown.
11 months ago
Adam Treat
e2458454d3
Bump to v2.4.12 and new release notes.
11 months ago
Adam Treat
d9f0245c1b
Fix problems with browse of folder in settings dialog.
11 months ago
Adam Treat
58d6f40f50
Fix broken installs.
11 months ago
Adam Treat
85626b3dab
Fix model path.
11 months ago
Adam Treat
ee73f1ab1d
Shrink the templates.
11 months ago
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>
11 months ago
Akarshan Biswas
16bd4a14d3
Add Qt6:WaylandClient only to Linux Build
...
Signed-off-by: Akarshan Biswas <akarshan.biswas@gmail.com>
11 months ago
Adam Treat
18316cde39
Bump to 2.4.12 and release notes.
11 months ago
Adam Treat
db528ef1b0
Add a close button for dialogs.
11 months ago
Adam Treat
27981c0d21
Fix broken download/remove/install.
11 months ago
Adam Treat
eab92a9d73
Fix typo and add new show references setting to localdocs.
11 months ago
Adam Treat
0638b45b47
Per model prompts / templates.
11 months ago
Adam Treat
1491c9fe49
Fix build on windows.
11 months ago
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.
11 months ago
Adam Treat
2a6c673c25
Begin redesign of settings dialog.
11 months ago
Adam Treat
dedb0025be
Refactor the settings dialog so that it uses a set of components/abstractions
...
for all of the tabs and stacks
11 months ago
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
11 months ago
matthew-gill
fd4081aed8
Update codeblock font
11 months ago
Lakshay Kansal
70cbff70cc
created highlighting rules for java using regex for the gpt4all chat interface
11 months ago
Adam Treat
1cd734efdc
Provide an abstraction to break up the settings dialog into managable pieces.
11 months ago
Adam Treat
7f252b4970
This completes the work of consolidating all settings that can be changed by the user on new settings object.
11 months ago
Adam Treat
285aa50b60
Consolidate generation and application settings on the new settings object.
11 months ago
Adam Treat
7f66c28649
Use the new settings for response generation.
11 months ago
Adam Treat
a8baa4da52
The sync for save should be after.
11 months ago
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.
11 months ago
Adam Treat
e70899a26c
Make the retrieval/parsing of models.json sync on startup. We were jumping to many hoops to mitigate the async behavior.
11 months ago
Adam Treat
9560336490
Match on the filename too for server mode.
11 months ago
Adam Treat
58cd346686
Bump release again and new release notes.
11 months ago
Adam Treat
0f8f364d76
Fix mac again for falcon.
11 months ago
Adam Treat
8aae4e52b3
Fix for falcon on mac.
11 months ago
Adam Treat
9375c71aa7
New release notes for 2.4.9 and bump version.
11 months ago
Adam Treat
71449bbc4b
Fix this correctly?
11 months ago
Adam Treat
07a5405618
Make it clear this is our finetune.
11 months ago
Adam Treat
189ac82277
Fix server mode.
11 months ago
Adam Treat
b56cc61ca2
Don't allow setting an invalid prompt template.
11 months ago
Adam Treat
0780393d00
Don't use local.
11 months ago
Adam Treat
924efd9e25
Add falcon to our models.json
11 months ago
Adam Treat
d3b8234106
Fix spelling.
11 months ago
Adam Treat
42c0a6673a
Don't persist the force metal setting.
11 months ago
Adam Treat
267601d670
Enable the force metal setting.
11 months ago
Aaron Miller
e22dd164d8
add falcon to chatllm::serialize
11 months ago
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
11 months ago
Adam Treat
985d3bbfa4
Add Orca models to list.
11 months ago
Adam Treat
8558fb4297
Fix models.json for spanning multiple lines with string.
11 months ago
Adam Treat
c24ad02a6a
Wait just a bit to set the model name so that we can display the proper name instead of filename.
11 months ago
Adam Treat
57fa8644d6
Make spelling check happy.
11 months ago
Adam Treat
d0a3e82ffc
Restore feature I accidentally erased in modellist update.
11 months ago
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)
11 months ago
Adam Treat
dead954134
Fix save chats setting.
11 months ago
Adam Treat
26c9193227
Sigh. Windows.
11 months ago
Adam Treat
5deec2afe1
Change this back now that it is ready.
11 months ago
Adam Treat
676248fe8f
Update the language.
11 months ago
Adam Treat
ef92492d8c
Add better warnings and links.
11 months ago
Adam Treat
71c972f8fa
Provide a more stark warning for localdocs and add more size to dialogs.
11 months ago
Adam Treat
1b5aa4617f
Enable the add button always, but show an error in placeholder text.
11 months ago
Adam Treat
a0f80453e5
Use sysinfo in backend.
11 months ago
Adam Treat
5e520bb775
Fix so that models are searched in subdirectories.
11 months ago
Adam Treat
64e98b8ea9
Fix bug with model loading on initial load.
11 months ago
Adam Treat
3ca9e8692c
Don't try and load incomplete files.
11 months ago
Adam Treat
27f25d5878
Get rid of recursive mutex.
11 months ago
Adam Treat
7f01b153b3
Modellist temp
11 months ago
Adam Treat
c1794597a7
Revert "Enable Wayland in build"
...
This reverts commit d686a583f9
.
11 months ago
Akarshan Biswas
d686a583f9
Enable Wayland in build
...
# Describe your changes
The patch include support for running natively on a Linux Wayland display server/compositor which is successor to old Xorg.
Cmakelist was missing WaylandClient so added it back.
Will fix #1047 .
Signed-off-by: Akarshan Biswas <akarshan.biswas@gmail.com>
11 months ago
AMOGUS
3417a37c54
Change "web server" to "API server" for less confusion ( #1039 )
...
* Change "Web server" to "API server"
* Changed "API server" to "OpenAPI server"
* Reversed back to "API server" and updated tooltip
12 months ago
cosmic-snow
a423075403
Allow Cross-Origin Resource Sharing (CORS) ( #1008 )
12 months ago
Martin Mauch
af28173a25
Parse Org Mode files ( #1038 )
12 months ago
niansa/tuxifan
01acb8d250
Update download speed less often
...
To not show every little tiny network spike to the user
Signed-off-by: niansa/tuxifan <tuxifan@posteo.de>
12 months ago
Adam Treat
09ae04cee9
This needs to work even when localdocs and codeblocks are detected.
12 months ago
Adam Treat
ce7333029f
Make the copy button a little more tolerant.
12 months ago
Adam Treat
508993de75
Exit early when no chats are saved.
12 months ago
Adam Treat
85bc861835
Fix the alignment.
12 months ago
Adam Treat
eebfe642c4
Add an error message to download dialog if models.json can't be retrieved.
12 months ago
Adam Treat
968868415e
Move saving chats to a thread and display what we're doing to the user.
12 months ago
Adam Treat
c8a590bc6f
Get rid of last blocking operations and make the chat/llm thread safe.
12 months ago
Adam Treat
84ec4311e9
Remove duplicated state tracking for chatgpt.
12 months ago
Adam Treat
7d2ce06029
Start working on more thread safety and model load error handling.
12 months ago
Adam Treat
d5f56d3308
Forgot to add a signal handler.
12 months ago
Adam Treat
aa2c824258
Initialize these.
12 months ago
Adam Treat
d018b4c821
Make this atomic.
12 months ago
Adam Treat
a3a6a20146
Don't store db results in ChatLLM.
12 months ago
Adam Treat
0cfe225506
Remove this as unnecessary.
12 months ago
Adam Treat
7c28e79644
Fix regenerate response with references.
12 months ago
AT
f76df0deac
Typescript ( #1022 )
...
* Show token generation speed in gui.
* Add typescript/javascript to list of highlighted languages.
12 months ago
AT
2b6cc99a31
Show token generation speed in gui. ( #1020 )
12 months ago
cosmic-snow
fd419caa55
Minor models.json description corrections. ( #1013 )
...
Signed-off-by: cosmic-snow <134004613+cosmic-snow@users.noreply.github.com>
12 months ago
Adam Treat
42e8049564
Bump version and new release notes for metal bugfix edition.
12 months ago
Adam Treat
e2c807d4df
Always install metal on apple.
12 months ago
Adam Treat
d5179ac0c0
Fix cmake build.
12 months ago
Adam Treat
d4283c0053
Fix metal and replit.
12 months ago
Adam Treat
0a0d4a714e
New release and bump the version.
12 months ago
Adam Treat
782e1e77a4
Fix up model names that don't begin with 'ggml-'
12 months ago
Adam Treat
b39a7d4fd9
Fix json.
12 months ago
Adam Treat
6690b49a9f
Converts the following to Q4_0
...
* Snoozy
* Nous Hermes
* Wizard 13b uncensored
Uses the filenames from actual download for these three.
12 months ago
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.
12 months ago
Adam Treat
8953b7f6a6
Fix regression in checked of db and network.
12 months ago
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)
12 months ago
Adam Treat
68ff7001ad
Bugfixes for prompt syntax highlighting.
12 months ago
Adam Treat
60d95cdd9b
Fix some bugs with bash syntax and add some C23 keywords.
12 months ago
Adam Treat
e986f18904
Add c++/c highighting support.
12 months ago
Adam Treat
ae46234261
Spelling error.
12 months ago
Adam Treat
318c51c141
Add code blocks and python syntax highlighting.
12 months ago
Adam Treat
b67cba19f0
Don't interfere with selection.
12 months ago
Adam Treat
50c5b82e57
Clean up the context links a bit.
12 months ago
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.
12 months ago
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>
12 months ago
Adam Treat
b162b5c64e
Revert "llama on Metal ( #885 )"
...
This reverts commit c55f81b860
.
12 months ago
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>
12 months ago
pingpongching
0d0fae0ca8
Change the default values for generation in GUI
12 months ago
Adam Treat
8fb73c2114
Forgot to bump.
12 months ago
Richard Guo
be2310322f
update models json with replit model
12 months ago
Andriy Mulyar
eb26293205
Update CollectionsDialog.qml ( #856 )
...
Phrasing for localdocs
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
1 year ago
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
1 year ago
Adam Treat
fdffad9efe
New release notes
1 year ago
Adam Treat
f5bdf7c94c
Bump the version.
1 year ago
Andriy Mulyar
d8e821134e
Revert "Fix bug with resetting context with chatgpt model." ( #859 )
...
This reverts commit 031d7149a7
.
1 year ago
Adam Treat
ecfeba2710
Revert "Speculative fix for windows llama models with installer."
...
This reverts commit c99e03e22e
.
1 year ago
Adam Treat
c99e03e22e
Speculative fix for windows llama models with installer.
1 year ago
AT
da757734ea
Release notes for version 2.4.5 ( #853 )
1 year ago
Adam Treat
969ff0ee6b
Fix installers for windows and linux.
1 year ago
Adam Treat
1d4c8e7091
These need to be installed for them to be packaged and work for both mac and windows.
1 year ago
Adam Treat
3a9cc329b1
Fix compile on mac.
1 year ago
Adam Treat
25eec33bda
Try and fix mac.
1 year ago
Adam Treat
91f20becef
Need this so the linux installer packages it as a dependency.
1 year ago
Adam Treat
812b2f4b29
Make installers work with mac/windows for big backend change.
1 year ago
Andriy Mulyar
2e5b114364
Update models.json
...
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
1 year ago
Andriy Mulyar
0db6fd6867
Update models.json ( #838 )
...
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
1 year ago
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>
1 year ago
Adam Treat
301d2fdbea
Fix up for newer models on reset context. This fixes the model from totally failing after a reset context.
1 year ago
Adam Treat
bdba2e8de6
Allow for download of models hosted on third party hosts.
1 year ago
Adam Treat
5073630759
Try again with the url.
1 year ago
Adam Treat
6ba37f47c1
Trying out a new feature to download directly from huggingface.
1 year ago
AT
be3c63ffcd
Update build_and_run.md ( #834 )
...
Signed-off-by: AT <manyoso@users.noreply.github.com>
1 year ago
AT
5f95aa9fc6
We no longer have an avx_only repository and better error handling for minimum hardware requirements. ( #833 )
1 year ago
Adam Treat
9f590db98d
Better error handling when the model fails to load.
1 year ago
AT
bbe195ee02
Backend prompt dedup ( #822 )
...
* Deduplicated prompt() function code
1 year ago
Adam Treat
bc624f5389
Add a collection immediately and show a placeholder + busy indicator in localdocs settings.
1 year ago
Adam Treat
55055ca983
Add the ability to change the directory via text field not just 'browse' button.
1 year ago
Adam Treat
25ee51e2ca
Actually use the theme dark color for window background.
1 year ago
Adam Treat
d9ddd373d6
Prevent flashing of white on resize.
1 year ago
Adam Treat
8aba76ad05
Min constraints on about dialog.
1 year ago
Adam Treat
a7f74e9d01
Some tweaks to UI to make window resizing smooth and flow nicely.
1 year ago
niansa/tuxifan
f3564ac6b9
Fixed tons of warnings and clazy findings ( #811 )
1 year ago
niansa/tuxifan
f0be66a221
Fixed spelling error in models.json
...
to make CI happy
Signed-off-by: niansa/tuxifan <tuxifan@posteo.de>
1 year ago
Adam Treat
be9f6ad543
Add models/release.json to github repo to allow PRs
1 year ago
Adam Treat
188770c92a
Remove this as it is no longer useful.
1 year ago
Adam Treat
a41bd6ac0a
Trying to shrink the copy+paste code and do more code sharing between backend model impl.
1 year ago
Adam Treat
031d7149a7
Fix bug with resetting context with chatgpt model.
1 year ago
Adam Treat
94633da2d7
Don't hardcode these.
1 year ago
Adam Treat
28944ac01b
Fix for stale references after we regenerate.
1 year ago
Adam Treat
aea94f756d
Better name for database results.
1 year ago