Adam Treat
a010a8a7ca
Bump version and release notes for v2.7.1
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
3 months ago
Jared Van Bortel
ef0a67eb94
models: remove gemma from models2.json and models3.json ( #1995 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
3 months ago
Adam Treat
67bbce43ab
Fix state issues with reloading model.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
3 months ago
Jared Van Bortel
4fc4d94be4
fix chat-style prompt templates ( #1970 )
...
Also use a new version of Mistral OpenOrca.
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
3 months ago
Jared Van Bortel
b8f5c74f40
add models3.json for new templates ( #1993 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
3 months ago
Jared Van Bortel
c13202a6f5
models2.json: gemma requires a future GPT4All version
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
3 months ago
Jared Van Bortel
4a8c6d7f9c
gemma: fix default prompt template
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
3 months ago
Jared Van Bortel
32837fb3a0
models2.json: add gemma model
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
3 months ago
Adam Treat
896fc6fbb7
Save the window size for the user and reuse next load.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
3 months ago
Adam Treat
fa0a2129dc
Don't try and detect model load error on startup.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
3 months ago
Adam Treat
b0c471aed8
Make the reload/regenerate buttons a little bit larger font.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
3 months ago
Adam Treat
67099f80ba
Add comment to make this clear.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
3 months ago
Adam Treat
ad34c2bdd4
Don't erase context when reloading model by selection.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
3 months ago
Adam Treat
fbf5e5e732
Increase padding for elided text in combo.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
3 months ago
Adam Treat
ed0f93977d
Fixes for issues identified in review.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
3 months ago
Adam Treat
d948a4f2ee
Complete revamp of model loading to allow for more discreet control by
...
the user of the models loading behavior.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
3 months ago
Adam Treat
16927d9a76
Fix visual artifact with close button in new version dialog.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
4 months ago
Adam Treat
f569ae9b22
Bump version and release notes for v2.7.0
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
4 months ago
Jared Van Bortel
2020c23edf
chat: set version to 2.7.0 ( #1940 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
4 months ago
Adam Treat
260a56c748
Don't show the download button if we are not connected to an online network.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
4 months ago
Adam Treat
4258bb1f8a
Fix issue 1918 for accessibility of screen readers.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
4 months ago
Adam Treat
490404dbb2
Fix issue 1925, scrollbar missing on main conversation.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
4 months ago
Jared Van Bortel
513a214eca
database: limit supported extensions to txt, pdf, md, rst
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
4 months ago
Jared Van Bortel
78a26cc5e4
models2.json: use ChatML for Mistral OpenOrca ( #1935 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
4 months ago
Adam Treat
1b524c4617
Reverse patch so we can minimize down to lowest HD form factor.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
4 months ago
Adam Treat
cb10465127
Make the collection dialog progress bar more readable.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
4 months ago
Adam Treat
4461af35c7
Fix includes.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
4 months ago
Jared Van Bortel
10e3f7bbf5
Fix VRAM leak when model loading fails ( #1901 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
4 months ago
Adam Treat
e1eac00ee0
Fix the download and settings dialog to take more real estate if available on large monitors.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
4 months ago
Adam Treat
111e152a5d
Fix the sizing for model download.
...
Signed-off-by: Adam Treat <adam@nomic.ai>
4 months ago
Adam Treat
ffed2ff823
Fix for progress bar color on legacy theme.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
4 months ago
Adam Treat
a5275ea9e7
Bump the version and release notes for v2.6.2.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
4 months ago
Adam Treat
cdf0fedae2
Make sure to use the search_query tag for nomic embed.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
4 months ago
Adam Treat
d14b95f4bd
Add Nomic Embed model for atlas with localdocs.
4 months ago
Jared Van Bortel
0a40e71652
Maxwell/Pascal GPU support and crash fix ( #1895 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
4 months ago
Jared Van Bortel
061d1969f8
expose n_gpu_layers parameter of llama.cpp ( #1890 )
...
Also dynamically limit the GPU layers and context length fields to the maximum supported by the model.
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
4 months ago
Jared Van Bortel
29d2c936d1
chat: don't show "retrieving localdocs" for zero collections ( #1874 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
4 months ago
Adam Treat
cfa22ab1c4
Change to a color that exists.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
4 months ago
Adam Treat
3556f63a29
Make the setting labels font a bit bigger and fix hover.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
4 months ago
Adam Treat
34de19ebf6
Add a legacy dark mode.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
4 months ago
Adam Treat
c1fce502f7
Fix checkbox background in dark mode.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
4 months ago
Adam Treat
363f6659e4
Fix the settings font size to be a tad bigger.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
4 months ago
Adam Treat
6abeefb303
Hover for links and increase font size a bit.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
4 months ago
Adam Treat
697a5f5d2a
New lightmode and darkmode themes with UI revamp.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
4 months ago
Karthik Nair
0a45dd384e
add fedora command for QT and related packages ( #1871 )
...
Signed-off-by: Karthik Nair <realkarthiknair@gmail.com>
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
4 months ago
Adam Treat
27912f6e1a
Fix bug with install of online models.
4 months ago
Jared Van Bortel
c7ea283f1f
chatllm: fix deserialization version mismatch ( #1859 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
4 months ago
Jared Van Bortel
b98e5f396a
docs: add missing dependencies to Linux build instructions ( #1728 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Adam Treat
e51a504550
Add the new 2.6.1 release notes and bump the version.
5 months ago
Jared Van Bortel
b803d51586
restore network.h #include
...
The online installers need this.
5 months ago
Jared Van Bortel
7e9786fccf
chat: set search path early
...
This fixes the issues with installed versions of v2.6.0.
5 months ago
Adam Treat
f7aeeca884
Revert the release.
5 months ago
Adam Treat
16a84972f6
Bump to new version and right the release notes.
5 months ago
Jared Van Bortel
4dbe2634aa
models2.json: update models list for the next release
5 months ago
Adam Treat
233f0c4201
Bump the version for our next release.
5 months ago
Gerhard Stein
3e99b90c0b
Some cleanps
5 months ago
Cal Alaera
528eb1e7ad
Update server.cpp to return valid created timestamps ( #1763 )
...
Signed-off-by: Cal Alaera <59891537+CalAlaera@users.noreply.github.com>
6 months ago
Jared Van Bortel
d1c56b8b28
Implement configurable context length ( #1749 )
6 months ago
Jared Van Bortel
3acbef14b7
fix AVX support by removing direct linking to AVX2 libs ( #1750 )
6 months ago
Jared Van Bortel
0600f551b3
chatllm: do not attempt to serialize incompatible state ( #1742 )
6 months ago
Adam Treat
fb3b1ceba2
Do not attempt to do a blocking retrieval if we don't have any collections.
6 months ago
Moritz Tim W
012f399639
fix typo ( #1697 )
6 months ago
Adam Treat
a328f9ed3f
Add a button to the collections dialog. Fix close button.
6 months ago
Adam Treat
e4ff972522
Bump and release v2.5.4
6 months ago
Adam Treat
4862e8b650
Networking retry on download error for models.
6 months ago
Jared Van Bortel
078c3bd85c
models2.json: add Orca 2 models ( #1672 )
6 months ago
Adam Treat
9e27a118ed
Fix system prompt.
6 months ago
Adam Treat
34555c4934
Bump version and release notes for v2.5.3
7 months ago
Adam Treat
9a3dd8815d
Fix GUI hang with localdocs by removing file system watcher in modellist.
7 months ago
Adam Treat
c1809a23ba
Fix text color on mac.
7 months ago
Adam Treat
59ed2a0bea
Use a global constant and remove a debug line.
7 months ago
Adam Treat
eecf351c64
Reduce copied code.
7 months ago
AT
abd4703c79
Update gpt4all-chat/embllm.cpp
...
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
Signed-off-by: AT <manyoso@users.noreply.github.com>
7 months ago
AT
4b413a60e4
Update gpt4all-chat/embeddings.cpp
...
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
Signed-off-by: AT <manyoso@users.noreply.github.com>
7 months ago
AT
17b346dfe7
Update gpt4all-chat/embeddings.cpp
...
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
Signed-off-by: AT <manyoso@users.noreply.github.com>
7 months ago
AT
71e37816cc
Update gpt4all-chat/qml/ModelDownloaderDialog.qml
...
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
Signed-off-by: AT <manyoso@users.noreply.github.com>
7 months ago
Adam Treat
371e2a5cbc
LocalDocs version 2 with text embeddings.
7 months ago
Adam Treat
bc88271520
Bump version to v2.5.3 and release notes.
7 months ago
cebtenzzre
5508e43466
build_and_run: clarify which additional Qt libs are needed
...
Signed-off-by: cebtenzzre <cebtenzzre@gmail.com>
7 months ago
cebtenzzre
79a5522931
fix references to old backend implementations
7 months ago
Adam Treat
f529d55380
Move this logic to QML.
7 months ago
Adam Treat
5c0d077f74
Remove leading whitespace in responses.
7 months ago
Adam Treat
131cfcdeae
Don't regenerate the name for deserialized chats.
7 months ago
Adam Treat
dc2e7d6e9b
Don't start recalculating context immediately upon switching to a new chat
...
but rather wait until the first prompt. This allows users to switch between
chats fast and to delete chats more easily.
Fixes issue #1545
7 months ago
Adam Treat
89a59e7f99
Bump version and add release notes for 2.5.1
7 months ago
cebtenzzre
f5dd74bcf0
models2.json: add tokenizer merges to mpt-7b-chat model ( #1563 )
7 months ago
cebtenzzre
e90263c23f
make scripts executable ( #1555 )
7 months ago
cebtenzzre
c25dc51935
chat: fix syntax error in main.qml
8 months ago
Victor Tsaran
721d854095
chat: improve accessibility fields ( #1532 )
...
Co-authored-by: cebtenzzre <cebtenzzre@gmail.com>
8 months ago
Adam Treat
9e99cf937a
Add release notes for 2.5.0 and bump the version.
8 months ago
cebtenzzre
245c5ce5ea
update default model URLs ( #1538 )
8 months ago
cebtenzzre
4338e72a51
MPT: use upstream llama.cpp implementation ( #1515 )
8 months ago
cebtenzzre
fd3014016b
docs: clarify Vulkan dep in build instructions for bindings ( #1525 )
8 months ago
cebtenzzre
ac33bafb91
docs: improve build_and_run.md ( #1524 )
8 months ago
Aaron Miller
10f9b49313
update mini-orca 3b to gguf2, license
...
Signed-off-by: Aaron Miller <apage43@ninjawhale.com>
8 months ago
niansa/tuxifan
a35f1ab784
Updated chat wishlist ( #1351 )
8 months ago
Adam Treat
908aec27fe
Always save chats to disk, but save them as text by default. This also changes
...
the UI behavior to always open a 'New Chat' and setting it as current instead
of setting a restored chat as current. This improves usability by not requiring
the user to wait if they want to immediately start chatting.
8 months ago
cebtenzzre
04499d1c7d
chatllm: do not write uninitialized data to stream ( #1486 )
8 months ago
Adam Treat
f0742c22f4
Restore state from text if necessary.
8 months ago
Adam Treat
35f9cdb70a
Do not delete saved chats if we fail to serialize properly.
8 months ago
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