Jared Van Bortel
7e1e00f331
chat: fix issues with quickly switching between multiple chats ( #2343 )
...
* prevent load progress from getting out of sync with the current chat
* fix memory leak on exit if the LLModelStore contains a model
* do not report cancellation as a failure in console/Mixpanel
* show "waiting for model" separately from "switching context" in UI
* do not show lower "reload" button on error
* skip context switch if unload is pending
* skip unnecessary calls to LLModel::saveState
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
4 months ago
Jared Van Bortel
7f1c3d4275
chatllm: fix model loading progress showing "Reload" sometimes ( #2337 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
4 months ago
AT
61cefcfd8a
Fix destruction and tear down of the embedding thread. ( #2328 )
...
* Fix destruction and tear down of the embedding thread.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
* Fix order of deletion to prevent use after free.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
---------
Signed-off-by: Adam Treat <treat.adam@gmail.com>
4 months ago
Jared Van Bortel
1427ef7195
chat: fix window icon on Windows ( #2321 )
...
* chat: fix window icon on Windows
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
* chat: remove redundant copy of macOS app icon
This has been redundant since PR #2180 .
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
---------
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
4 months ago
Tim453
69720fedaa
Update appdata.xml ( #2307 )
4 months ago
Jared Van Bortel
5fb9d17c00
chatllm: use a better prompt for the generated chat name ( #2322 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
4 months ago
Jared Van Bortel
f26e8d0d87
chat: do not allow sending a message while the LLM is responding ( #2323 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
4 months ago
Jared Van Bortel
d54e644d05
ChatView: make context menus more intuitive ( #2324 )
...
* ChatView: fix deprecation warning
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
* ChatView: make context menus more intuitive
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
---------
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
4 months ago
Jared Van Bortel
26eaf598b4
chat: add release notes for v2.7.5 and bump version ( #2300 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel
577ebd4826
mixpanel: report cpu_supports_avx2 on startup ( #2299 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel
855fd22417
localdocs: load model before checking which model is loaded ( #2284 )
...
* localdocs: load model before checking what we loaded
Fixes "WARNING: Request to generate sync embeddings for non-local model
invalid"
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
* fix inverted assertion
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
---------
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel
adaecb7a72
mixpanel: improved GPU device statistics (plus GPU sort order fix) ( #2297 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel
27c561aeb7
mixpanel: fix opt-out events after #2238 ( #2296 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel
6f38fde80b
mixpanel: fix doc_collections_total of localdocs_startup ( #2270 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel
a14193623a
chat: add release notes for v2.7.4 and bump version ( #2269 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel
4f3c9bbe3e
network: fix use of GNU asm statement with MSVC ( #2267 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel
c622921894
improve mixpanel usage statistics ( #2238 )
...
Other changes:
- Always display first start dialog if privacy options are unset (e.g. if the user closed GPT4All without selecting them)
- LocalDocs scanQueue is now always deferred
- Fix a potential crash in magic_match
- LocalDocs indexing is now started after the first start dialog is dismissed so usage stats are included
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel
4193533154
models.json: add Phi-3 Mini Instruct ( #2252 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel
0b78b79b1c
models.json: add Llama 3 Instruct 8B ( #2242 )
...
Other changes:
* fix 'requires' for models with %2 in template
* move Ghost 7B to the appropriate location in the file based on where it actually appears in the UI
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel
aac00d019a
chat: temporarily revert some UI changes before next release ( #2234 )
...
* chat: revert PR #2187
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
* chat: revert PR #2148
This reverts commit f571e7e450
.
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
---------
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel
271d752701
localdocs: small but important fixes to local docs ( #2236 )
...
* chat: use .rmodel extension for Nomic Embed
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
* database: fix order of SQL arguments in updateDocument
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
---------
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel
be93ee75de
responsetext : fix markdown code block trimming ( #2232 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Jared Van Bortel
38cc778a0c
models.json: use simpler system prompt for Mistral OpenOrca ( #2220 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Adam Treat
94a9943782
Change the behavior of show references setting for localdocs.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
5 months ago
Adam Treat
e27653219b
Fix bugs with the context link text for localdocs to make the context links
...
persistently work across application loads and fix scrolling bug with context
links.
Signed-off-by: Adam Treat <treat.adam@gmail.com>
5 months ago
Jared Van Bortel
ac498f79ac
fix regressions in system prompt handling ( #2219 )
...
* python: fix system prompt being ignored
* fix unintended whitespace after system prompt
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
5 months ago
Adam Treat
790320e170
Use consistent names for LocalDocs
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Adam Treat
aad502f336
Rename these to views.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
Adam Treat
77d5adfb02
Changes to the UI and icons.
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
6 months ago
3Simplex
9c23d44ad3
Update ChatView.qml
...
Directed the Documentation link specifically to the ChatUI documentation.
Co-authored-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
Signed-off-by: 3Simplex <10260755+3Simplex@users.noreply.github.com>
6 months ago
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