3Simplex
4f6c43aec9
Update ChatView.qml
...
Include links for Documentation and FAQ for new users on the "new chat view".
Co-authored-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
Signed-off-by: 3Simplex <10260755+3Simplex@users.noreply.github.com>
6 months ago
Robin Verduijn
4852d39699
Fix to set proper app icon on MacOS.
...
Signed-off-by: Robin Verduijn <robinverduijn.github@gmail.com>
6 months ago
Adam Treat
b4bcc5b37c
Fix colors for server chat in all themes.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Adam Treat
f571e7e450
Preliminary redesign of the UI. This has no major regression.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Lam Hieu
271e6a529c
Rename the model for more clarity
...
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
6 months ago
Lam Hieu
5732928b93
Change download url
...
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
6 months ago
Lam Hieu
6a22b81f44
Update Ghost 7B v0.9.1 configuration
...
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
6 months ago
Lam Hieu
f50bf856b3
Fix invalid model configuration
...
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
6 months ago
Lam Hieu
df79e45195
Support Ghost 7B v0.9.1, fast, powerful and smooth for Vietnamese and English languages.
...
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
6 months ago
Jared Van Bortel
699410014a
fix non-AVX CPU detection ( #2141 )
...
* chat: fix non-AVX CPU detection on Windows
* bindings: throw exception instead of logging to console
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
6 months ago
Tim453
6c2542e540
Allow changing the install path
...
This commit allow changing the install path during CMake configure step using the CMAKE_INSTALL_PREFIX variable. If the variable is not set, it still defaults to {CMAKE_BINARY_DIR}/install.
Signed-off-by: Tim453 <50015765+Tim453@users.noreply.github.com>
6 months ago
Jared Van Bortel
255568fb9a
python: various fixes for GPT4All and Embed4All ( #2130 )
...
Key changes:
* honor empty system prompt argument
* current_chat_session is now read-only and defaults to None
* deprecate fallback prompt template for unknown models
* fix mistakes from #2086
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
6 months ago
Adam Treat
667f29c2a1
Split the main.qml into two pieces to support multiple views in future.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Adam Treat
97de30edd1
Fix bug with removing old .txt chatgpt files in favor of .rmodel
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Olyxz16
2c0a660e6e
feat: Add support for Mistral API models ( #2053 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Signed-off-by: Cédric Sazos <cedric.sazos@tutanota.com>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
6 months ago
Jared Van Bortel
406e88b59a
implement local Nomic Embed via llama.cpp ( #2086 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
6 months ago
Adam Treat
171f4e488e
Restrict the chat view text width to a reasonable maximum.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Adam Treat
6adaa672b4
Default to expanded state.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Adam Treat
b68ebb7c15
Rework the left chat panel to be persistently open.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Xu Zhen
0072860d24
Fix compatibility with Qt 6.4
...
Signed-off-by: Xu Zhen <xuzhen@users.noreply.github.com>
6 months ago
Adam Treat
ef9717dbe9
Use translation function for newly introduced strings.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Kryotek
afbb30a523
Add context menus to the prompt and the responses
...
Signed-off-by: Kryotek <gcda@outlook.it>
6 months ago
Adam Treat
11db71e0a7
Bump version and release notes for v2.7.3
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Adam Treat
5ed9aea410
Don't clear installed models.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Adam Treat
e2f64f89c9
When the current chat has no model use the first index.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Adam Treat
0daf37ab8a
Fixes issue #2105 by using the original url for the download. This fix is
...
valid because we expect the url to contain the actual filename at the end.
This also allows huggingface to track the download as happening.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Adam Treat
a6a3e0048a
Don't erase the settings, but ignore them.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Adam Treat
f36a2874eb
Clean up settings properly for removed models and also when user manually deletes.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
chrisbarrera
61d6765361
#2024 Update ModelSettings.qml to default model/char settings combobox to the currently selected chat model
...
Signed-off-by: chrisbarrera <34655880+chrisbarrera@users.noreply.github.com>
6 months ago
Adam Treat
59f99b7f21
Minor fixes to server port feature.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Daniel Alencar
fe653d1489
feat: added api server port setting
6 months ago
Jared Van Bortel
5c248dbec9
models: new MPT model file without duplicated token_embd.weight ( #2006 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Adam Treat
6ed3d01f17
Fix issue #2087 where cloned models were lost and listed in download dialog erroneously.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat
6c3903a303
Fixes issue #2092 . Don't include disabled from GUI models in application
...
default model list.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat
8ee68d1b6f
Increase indent for readability.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat
4251b7beaa
Fix issue #2077 part 2. Only sort when actually necessary.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat
fc169e739a
Add trailing commas for things that need to be added in the future.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat
028a8db6ba
No need to use equals here.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat
26cedb83b0
Use initializer lists instead of append where applicable.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat
9c755d25c4
Get rid of unnecessary qMakePair
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat
099459c8b9
Update batch patch following review.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
AT
8474d76fec
Update gpt4all-chat/download.cpp
...
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
Signed-off-by: AT <manyoso@users.noreply.github.com>
7 months ago
Adam Treat
08b5dc8598
Batch all operations for updateData to avoid excessive sort.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat
17dee02287
Fix for issue #2080 where the GUI appears to hang when a chat with a large
...
model is deleted. There is no reason to save the context for a chat that
is being deleted.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Jared Van Bortel
44717682a7
chat: implement display of model loading warnings ( #2034 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Jared Van Bortel
a0bd96f75d
chat: join ChatLLM threads without calling destructors ( #2043 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Jared Van Bortel
5a874be7c1
modellist: rename "deprecated" to "removedIn", disable if equal ( #2063 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Jared Van Bortel
402f515a5d
chat: fix ChatGPT after #1970 ( #2051 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Jared Van Bortel
2a91ffd73f
chatllm: fix undefined behavior in resetContext
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Jared Van Bortel
0fc071d228
chat: better handle case where network reachability is unknown
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Adam Treat
be6d3bf9dc
Bump version and release notes for 2.7.2
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat
83c76be68a
Model discovery.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
ThiloteE
f2b4809b72
models3: remove system prompt of Nous-Hermes-2-Mistral-7b-DPO ( #2054 )
...
Signed-off-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
7 months ago
Jared Van Bortel
9fafca5c94
qml: update models.json URL in error message
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Adam Treat
7d1e30766f
Fix the hash on the new model.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat
5ddcf61ae4
Shorten the description and provide a valid url.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
ThiloteE
713afb7070
Add-Nous-Hermes-2-Mistral-7B-DPO.Q4_0.gguf
...
Adds Nous-Hermes-2-Mistral-7B-DPO.Q4_0.gguf, which is the new 7b flagship model of NousResearch.
**Original Model location:**
https://huggingface.co/NousResearch/Nous-Hermes-2-Mistral-7B-DPO-GGUF
**Model description:**
Nous Hermes 2 on Mistral 7B DPO is the new flagship 7B Hermes! This model was DPO'd from Teknium/OpenHermes-2.5-Mistral-7B and has improved across the board on all benchmarks tested - AGIEval, BigBench Reasoning, GPT4All, and TruthfulQA.
The model prior to DPO was trained on 1,000,000 instructions/chats of GPT-4 quality or better, primarily synthetic data as well as other high quality datasets, available from the repository teknium/OpenHermes-2.5.
**Original Dataset Location:**
https://huggingface.co/datasets/teknium/OpenHermes-2.5
**Dataset description:**
This is the dataset that made OpenHermes 2.5 and Nous Hermes 2 series of models.
The Open Hermes 2/2.5 and Nous Hermes 2 models have made significant advancements of SOTA LLM's over recent months, and are underpinned by this exact compilation and curation of many open source datasets and custom created synthetic datasets.
The Open Hermes 2.5 dataset is a continuation of the Open Hermes 1 dataset, at a much larger scale, much more diverse, and much higher quality compilation, reaching 1M, primarily synthetically generated instruction and chat samples.
Signed-off-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
7 months ago
Jared Van Bortel
f500bcf6e5
llmodel: default to a blank line between reply and next prompt ( #1996 )
...
Also make some related adjustments to the provided Alpaca-style prompt templates
and system prompts.
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Jared Van Bortel
fc1a281381
modellist: fix bad copy-paste in ModelList::clone ( #2011 )
...
s/contextLength/gpuLayers/
Fixes #2010
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
AT
7a23b23728
Update gpt4all-chat/modellist.cpp
...
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
Signed-off-by: AT <manyoso@users.noreply.github.com>
7 months ago
Adam Treat
17a2cdbe35
Fix crasher with layer count
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
chrisbarrera
f8b1069a1c
add min_p sampling parameter ( #2014 )
...
Signed-off-by: Christopher Barrera <cb@arda.tx.rr.com>
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
7 months ago
Adam Treat
ef518fae3e
Fix crash with chatgpt and gpu layers.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Jared Van Bortel
c1dcb3f5b8
models.json: fix Mistral OpenOrca filename
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Adam Treat
a010a8a7ca
Bump version and release notes for v2.7.1
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 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>
7 months ago
Adam Treat
67bbce43ab
Fix state issues with reloading model.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 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>
7 months ago
Jared Van Bortel
b8f5c74f40
add models3.json for new templates ( #1993 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Jared Van Bortel
c13202a6f5
models2.json: gemma requires a future GPT4All version
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Jared Van Bortel
4a8c6d7f9c
gemma: fix default prompt template
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 months ago
Jared Van Bortel
32837fb3a0
models2.json: add gemma model
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
7 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>
7 months ago
Adam Treat
fa0a2129dc
Don't try and detect model load error on startup.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat
b0c471aed8
Make the reload/regenerate buttons a little bit larger font.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat
67099f80ba
Add comment to make this clear.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat
ad34c2bdd4
Don't erase context when reloading model by selection.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat
fbf5e5e732
Increase padding for elided text in combo.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat
ed0f93977d
Fixes for issues identified in review.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 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>
7 months ago
Adam Treat
16927d9a76
Fix visual artifact with close button in new version dialog.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Adam Treat
f569ae9b22
Bump version and release notes for v2.7.0
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
7 months ago
Jared Van Bortel
2020c23edf
chat: set version to 2.7.0 ( #1940 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
8 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>
8 months ago
Adam Treat
4258bb1f8a
Fix issue 1918 for accessibility of screen readers.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Adam Treat
490404dbb2
Fix issue 1925, scrollbar missing on main conversation.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Jared Van Bortel
513a214eca
database: limit supported extensions to txt, pdf, md, rst
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
8 months ago
Jared Van Bortel
78a26cc5e4
models2.json: use ChatML for Mistral OpenOrca ( #1935 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
8 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>
8 months ago
Adam Treat
cb10465127
Make the collection dialog progress bar more readable.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Adam Treat
4461af35c7
Fix includes.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Jared Van Bortel
10e3f7bbf5
Fix VRAM leak when model loading fails ( #1901 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
8 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>
8 months ago
Adam Treat
111e152a5d
Fix the sizing for model download.
...
Signed-off-by: Adam Treat <adam@nomic.ai>
8 months ago
Adam Treat
ffed2ff823
Fix for progress bar color on legacy theme.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Adam Treat
a5275ea9e7
Bump the version and release notes for v2.6.2.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 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>
8 months ago
Adam Treat
d14b95f4bd
Add Nomic Embed model for atlas with localdocs.
8 months ago
Jared Van Bortel
0a40e71652
Maxwell/Pascal GPU support and crash fix ( #1895 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
8 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>
8 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>
8 months ago
Adam Treat
cfa22ab1c4
Change to a color that exists.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 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>
8 months ago
Adam Treat
34de19ebf6
Add a legacy dark mode.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Adam Treat
c1fce502f7
Fix checkbox background in dark mode.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Adam Treat
363f6659e4
Fix the settings font size to be a tad bigger.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Adam Treat
6abeefb303
Hover for links and increase font size a bit.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 months ago
Adam Treat
697a5f5d2a
New lightmode and darkmode themes with UI revamp.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
8 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>
8 months ago
Adam Treat
27912f6e1a
Fix bug with install of online models.
8 months ago
Jared Van Bortel
c7ea283f1f
chatllm: fix deserialization version mismatch ( #1859 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
8 months ago
Jared Van Bortel
b98e5f396a
docs: add missing dependencies to Linux build instructions ( #1728 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
8 months ago
Adam Treat
e51a504550
Add the new 2.6.1 release notes and bump the version.
8 months ago
Jared Van Bortel
b803d51586
restore network.h #include
...
The online installers need this.
8 months ago
Jared Van Bortel
7e9786fccf
chat: set search path early
...
This fixes the issues with installed versions of v2.6.0.
8 months ago
Adam Treat
f7aeeca884
Revert the release.
8 months ago
Adam Treat
16a84972f6
Bump to new version and right the release notes.
8 months ago
Jared Van Bortel
4dbe2634aa
models2.json: update models list for the next release
8 months ago
Adam Treat
233f0c4201
Bump the version for our next release.
9 months ago
Gerhard Stein
3e99b90c0b
Some cleanps
9 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>
9 months ago
Jared Van Bortel
d1c56b8b28
Implement configurable context length ( #1749 )
9 months ago
Jared Van Bortel
3acbef14b7
fix AVX support by removing direct linking to AVX2 libs ( #1750 )
9 months ago
Jared Van Bortel
0600f551b3
chatllm: do not attempt to serialize incompatible state ( #1742 )
9 months ago
Adam Treat
fb3b1ceba2
Do not attempt to do a blocking retrieval if we don't have any collections.
10 months ago
Moritz Tim W
012f399639
fix typo ( #1697 )
10 months ago
Adam Treat
a328f9ed3f
Add a button to the collections dialog. Fix close button.
10 months ago
Adam Treat
e4ff972522
Bump and release v2.5.4
10 months ago
Adam Treat
4862e8b650
Networking retry on download error for models.
10 months ago
Jared Van Bortel
078c3bd85c
models2.json: add Orca 2 models ( #1672 )
10 months ago
Adam Treat
9e27a118ed
Fix system prompt.
10 months ago
Adam Treat
34555c4934
Bump version and release notes for v2.5.3
10 months ago
Adam Treat
9a3dd8815d
Fix GUI hang with localdocs by removing file system watcher in modellist.
10 months ago
Adam Treat
c1809a23ba
Fix text color on mac.
10 months ago
Adam Treat
59ed2a0bea
Use a global constant and remove a debug line.
10 months ago
Adam Treat
eecf351c64
Reduce copied code.
10 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>
10 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>
10 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>
10 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>
10 months ago
Adam Treat
371e2a5cbc
LocalDocs version 2 with text embeddings.
10 months ago
Adam Treat
bc88271520
Bump version to v2.5.3 and release notes.
11 months ago
cebtenzzre
5508e43466
build_and_run: clarify which additional Qt libs are needed
...
Signed-off-by: cebtenzzre <cebtenzzre@gmail.com>
11 months ago
cebtenzzre
79a5522931
fix references to old backend implementations
11 months ago
Adam Treat
f529d55380
Move this logic to QML.
11 months ago
Adam Treat
5c0d077f74
Remove leading whitespace in responses.
11 months ago
Adam Treat
131cfcdeae
Don't regenerate the name for deserialized chats.
11 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
11 months ago
Adam Treat
89a59e7f99
Bump version and add release notes for 2.5.1
11 months ago
cebtenzzre
f5dd74bcf0
models2.json: add tokenizer merges to mpt-7b-chat model ( #1563 )
11 months ago
cebtenzzre
e90263c23f
make scripts executable ( #1555 )
11 months ago
cebtenzzre
c25dc51935
chat: fix syntax error in main.qml
11 months ago
Victor Tsaran
721d854095
chat: improve accessibility fields ( #1532 )
...
Co-authored-by: cebtenzzre <cebtenzzre@gmail.com>
11 months ago
Adam Treat
9e99cf937a
Add release notes for 2.5.0 and bump the version.
11 months ago
cebtenzzre
245c5ce5ea
update default model URLs ( #1538 )
11 months ago
cebtenzzre
4338e72a51
MPT: use upstream llama.cpp implementation ( #1515 )
11 months ago
cebtenzzre
fd3014016b
docs: clarify Vulkan dep in build instructions for bindings ( #1525 )
11 months ago
cebtenzzre
ac33bafb91
docs: improve build_and_run.md ( #1524 )
11 months ago
Aaron Miller
10f9b49313
update mini-orca 3b to gguf2, license
...
Signed-off-by: Aaron Miller <apage43@ninjawhale.com>
11 months ago
niansa/tuxifan
a35f1ab784
Updated chat wishlist ( #1351 )
11 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.
11 months ago
cebtenzzre
04499d1c7d
chatllm: do not write uninitialized data to stream ( #1486 )
11 months ago
Adam Treat
f0742c22f4
Restore state from text if necessary.
11 months ago
Adam Treat
35f9cdb70a
Do not delete saved chats if we fail to serialize properly.
11 months ago
cebtenzzre
9fb135e020
cmake: install the GPT-J plugin ( #1487 )
12 months ago
Aaron Miller
3c25d81759
make codespell happy
12 months ago
Jan Philipp Harries
4f0cee9330
added EM German Mistral Model
12 months ago
Adam Treat
56c0d2898d
Update the language here to avoid misunderstanding.
12 months ago
Adam Treat
b2cd3bdb3f
Fix crasher with an empty string for prompt template.
12 months ago
Cebtenzzre
5fe685427a
chat: clearer CPU fallback messages
12 months ago
Aaron Miller
9325075f80
fix stray comma in models2.json
...
Signed-off-by: Aaron Miller <apage43@ninjawhale.com>
12 months ago
Adam Treat
f028f67c68
Add starcoder, rift and sbert to our models2.json.
12 months ago
Adam Treat
4528f73479
Reorder and refresh our models2.json.
12 months ago
Cebtenzzre
1534df3e9f
backend: do not use Vulkan with non-LLaMA models
12 months ago
Cebtenzzre
672cb850f9
differentiate between init failure and unsupported models
12 months ago
Cebtenzzre
a5b93cf095
more accurate fallback descriptions
12 months ago
Cebtenzzre
75deee9adb
chat: make sure to clear fallback reason on success
12 months ago
Cebtenzzre
2eb83b9f2a
chat: report reason for fallback to CPU
12 months ago
Adam Treat
ea66669cef
Switch to new models2.json for new gguf release and bump our version to
...
2.5.0.
12 months ago
Adam Treat
12f943e966
Fix regenerate button to be deterministic and bump the llama version to latest we have for gguf.
12 months ago
Cebtenzzre
a49a1dcdf4
chatllm: grammar fix
12 months ago
Cebtenzzre
31b20f093a
modellist: fix the system prompt
12 months ago
Cebtenzzre
8f3abb37ca
fix references to removed model types
12 months ago
Adam Treat
d90d003a1d
Latest rebase on llama.cpp with gguf support.
12 months ago
Akarshan Biswas
5f3d739205
appdata: update software description
12 months ago
Akarshan Biswas
b4cf12e1bd
Update to 2.4.19
12 months ago
Akarshan Biswas
21a5709b07
Remove unnecessary stuffs from manifest
12 months ago
Akarshan Biswas
4426640f44
Add flatpak manifest
12 months ago
Aaron Miller
6711bddc4c
launch browser instead of maintenancetool from offline builds
12 months ago
Aaron Miller
7f979c8258
Build offline installers in CircleCI
12 months ago
Adam Treat
dc80d1e578
Fix up the offline installer.
1 year ago
Adam Treat
f47e698193
Release notes for v2.4.19 and bump the version.
1 year ago
Adam Treat
ecf014f03b
Release notes for v2.4.18 and bump the version.
1 year ago
Adam Treat
e6e724d2dc
Actually bump the version.
1 year ago
Adam Treat
06a833e652
Send actual and requested device info for those who have opt-in.
1 year ago
Adam Treat
045f6e6cdc
Link against ggml in bin so we can get the available devices without loading a model.
1 year ago
Adam Treat
655372dbfa
Release notes for v2.4.17 and bump the version.
1 year ago
Adam Treat
aa33419c6e
Fallback to CPU more robustly.
1 year ago
Adam Treat
79843c269e
Release notes for v2.4.16 and bump the version.
1 year ago
Adam Treat
3076e0bf26
Only show GPU when we're actually using it.
1 year ago
Adam Treat
1fa67a585c
Report the actual device we're using.
1 year ago
Adam Treat
21a3244645
Fix a bug where we're not properly falling back to CPU.
1 year ago
Adam Treat
0458c9b4e6
Add version 2.4.15 and bump the version number.
1 year ago
Aaron Miller
6f038c136b
init at most one vulkan device, submodule update
...
fixes issues w/ multiple of the same gpu
1 year ago
Adam Treat
86e862df7e
Fix up the name and formatting.
1 year ago
Adam Treat
358ff2a477
Show the device we're currently using.
1 year ago
Adam Treat
891ddafc33
When device is Auto (the default) then we will only consider discrete GPU's otherwise fallback to CPU.
1 year ago
Adam Treat
8f99dca70f
Bring the vulkan backend to the GUI.
1 year ago
Adam Treat
987546c63b
Nomic vulkan backend licensed under the Software for Open Models License (SOM), version 1.0.
1 year ago
Adam Treat
d55cbbee32
Update to newer llama.cpp and disable older forks.
1 year ago
Adam Treat
a63093554f
Remove older models that rely upon soon to be no longer supported quantization formats.
1 year ago
Adam Treat
2c0ee50dce
Add starcoder 7b.
1 year ago
Victor Tsaran
ca8baa294b
Updated README.md with a wishlist idea ( #1315 )
...
Signed-off-by: Victor Tsaran <vtsaran@yahoo.com>
1 year ago
Lakshay Kansal
0f2bb506a8
font size changer and updates ( #1322 )
1 year 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>
1 year ago
Lakshay Kansal
cbdcde8b75
scrollbar fixed for main chat and chat drawer ( #1301 )
1 year ago
Lakshay Kansal
3d2db76070
fixed issue of text color changing for code blocks in light mode ( #1299 )
1 year ago
Aaron Miller
b9e2553995
remove trailing comma from models json ( #1284 )
1 year ago
Adam Treat
09a143228c
New release notes and bump version.
1 year ago
Lakshay Kansal
fc1af4a234
light mode vs dark mode
1 year ago
Adam Treat
6d03b3e500
Add starcoder support.
1 year ago
Adam Treat
397f3ba2d7
Add a little size to the monospace font.
1 year 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>
1 year ago
Lakshay Kansal
6c8669cad3
highlighting rules for html and php and latex
1 year ago
Adam Treat
0efdbfcffe
Bert
1 year ago
Adam Treat
315a1f2aa2
Move it back as internal class.
1 year ago
Adam Treat
ae8eb297ac
Add sbert backend.
1 year ago
Adam Treat
1f749d7633
Clean up backend code a bit and hide impl. details.
1 year ago
Adam Treat
a0dae86a95
Add bert to models.json
1 year ago
AT
18ca8901f0
Update README.md
...
Signed-off-by: AT <manyoso@users.noreply.github.com>
1 year ago
Adam Treat
e8b19b8e82
Bump version to 2.4.14 and provide release notes.
1 year ago
Adam Treat
8eb0844277
Check if the trimmed version is empty.
1 year ago
Adam Treat
be395c12cc
Make all system prompts empty by default if model does not include in training data.
1 year 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.
1 year ago
Adam Treat
8893db5896
Add wizard model and rename orca to be more specific.
1 year ago
Adam Treat
60627bd41f
Prefer 7b models in order of default model load.
1 year ago
Aaron Miller
5df4f1bf8c
codespell
1 year ago
Aaron Miller
10ca2c4475
center the spinner
1 year ago
Adam Treat
e9897518d1
Show busy if models.json download taking longer than expected.
1 year ago
Aaron Miller
ad0e7fd01f
chatgpt: ensure no extra newline in header
1 year 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
1 year ago
Adam Treat
0d726b22b8
When we explicitly cancel an operation we shouldn't throw an error.
1 year ago
Adam Treat
13b2d47be5
Provide an error dialog if for any reason we can't access the settings file.
1 year ago
Adam Treat
e9d42fba35
Don't show first start more than once.
1 year ago
Adam Treat
2679dc1521
Give note about gpt-4 and openai key access.
1 year ago
Adam Treat
806905f747
Explicitly set the color in MyTextField.
1 year ago
Adam Treat
9dccc96e70
Immediately signal when the model is in a new loading state.
1 year ago
Adam Treat
833a56fadd
Fix the tap handler on these buttons.
1 year ago
Adam Treat
18dbfddcb3
Fix default thread setting.
1 year ago
Adam Treat
34a3b9c857
Don't block on exit when not connected.
1 year ago