536 Commits (main)

Author	SHA1	Message	Date
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