276 Commits (ee4186d579858c9b727d919ebfa102f9c53d65c1)

Author	SHA1	Message	Date
Adam Treat	eab92a9d73	Fix typo and add new show references setting to localdocs.	1 year ago
Adam Treat	0638b45b47	Per model prompts / templates.	1 year ago
Adam Treat	1491c9fe49	Fix build on windows.	1 year 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.	1 year ago
Adam Treat	2a6c673c25	Begin redesign of settings dialog.	1 year ago
Adam Treat	dedb0025be	Refactor the settings dialog so that it uses a set of components/abstractions ... for all of the tabs and stacks	1 year 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	1 year ago
matthew-gill	fd4081aed8	Update codeblock font	1 year ago
Lakshay Kansal	70cbff70cc	created highlighting rules for java using regex for the gpt4all chat interface	1 year ago
Adam Treat	1cd734efdc	Provide an abstraction to break up the settings dialog into managable pieces.	1 year ago
Adam Treat	7f252b4970	This completes the work of consolidating all settings that can be changed by the user on new settings object.	1 year ago
Adam Treat	285aa50b60	Consolidate generation and application settings on the new settings object.	1 year ago
Adam Treat	7f66c28649	Use the new settings for response generation.	1 year ago
Adam Treat	a8baa4da52	The sync for save should be after.	1 year 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.	1 year 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.	1 year ago
Adam Treat	9560336490	Match on the filename too for server mode.	1 year ago
Adam Treat	58cd346686	Bump release again and new release notes.	1 year ago
Adam Treat	0f8f364d76	Fix mac again for falcon.	1 year ago
Adam Treat	8aae4e52b3	Fix for falcon on mac.	1 year ago
Adam Treat	9375c71aa7	New release notes for 2.4.9 and bump version.	1 year ago
Adam Treat	71449bbc4b	Fix this correctly?	1 year ago
Adam Treat	07a5405618	Make it clear this is our finetune.	1 year ago
Adam Treat	189ac82277	Fix server mode.	1 year ago
Adam Treat	b56cc61ca2	Don't allow setting an invalid prompt template.	1 year ago
Adam Treat	0780393d00	Don't use local.	1 year ago
Adam Treat	924efd9e25	Add falcon to our models.json	1 year ago
Adam Treat	d3b8234106	Fix spelling.	1 year ago
Adam Treat	42c0a6673a	Don't persist the force metal setting.	1 year ago
Adam Treat	267601d670	Enable the force metal setting.	1 year ago
Aaron Miller	e22dd164d8	add falcon to chatllm::serialize	1 year 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	1 year ago
Adam Treat	985d3bbfa4	Add Orca models to list.	1 year ago
Adam Treat	8558fb4297	Fix models.json for spanning multiple lines with string.	1 year ago
Adam Treat	c24ad02a6a	Wait just a bit to set the model name so that we can display the proper name instead of filename.	1 year ago
Adam Treat	57fa8644d6	Make spelling check happy.	1 year ago
Adam Treat	d0a3e82ffc	Restore feature I accidentally erased in modellist update.	1 year 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)	1 year ago
Adam Treat	dead954134	Fix save chats setting.	1 year ago
Adam Treat	26c9193227	Sigh. Windows.	1 year ago
Adam Treat	5deec2afe1	Change this back now that it is ready.	1 year ago
Adam Treat	676248fe8f	Update the language.	1 year ago
Adam Treat	ef92492d8c	Add better warnings and links.	1 year ago
Adam Treat	71c972f8fa	Provide a more stark warning for localdocs and add more size to dialogs.	1 year ago
Adam Treat	1b5aa4617f	Enable the add button always, but show an error in placeholder text.	1 year ago
Adam Treat	a0f80453e5	Use sysinfo in backend.	1 year ago
Adam Treat	5e520bb775	Fix so that models are searched in subdirectories.	1 year ago
Adam Treat	64e98b8ea9	Fix bug with model loading on initial load.	1 year ago
Adam Treat	3ca9e8692c	Don't try and load incomplete files.	1 year ago
Adam Treat	27f25d5878	Get rid of recursive mutex.	1 year ago
Adam Treat	7f01b153b3	Modellist temp	1 year ago
Adam Treat	c1794597a7	Revert "Enable Wayland in build" ... This reverts commit d686a583f9.	1 year 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>	1 year 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	1 year ago
cosmic-snow	a423075403	Allow Cross-Origin Resource Sharing (CORS) (#1008)	1 year ago
Martin Mauch	af28173a25	Parse Org Mode files (#1038)	1 year 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>	1 year ago
Adam Treat	09ae04cee9	This needs to work even when localdocs and codeblocks are detected.	1 year ago
Adam Treat	ce7333029f	Make the copy button a little more tolerant.	1 year ago
Adam Treat	508993de75	Exit early when no chats are saved.	1 year ago
Adam Treat	85bc861835	Fix the alignment.	1 year ago
Adam Treat	eebfe642c4	Add an error message to download dialog if models.json can't be retrieved.	1 year ago
Adam Treat	968868415e	Move saving chats to a thread and display what we're doing to the user.	1 year ago
Adam Treat	c8a590bc6f	Get rid of last blocking operations and make the chat/llm thread safe.	1 year ago
Adam Treat	84ec4311e9	Remove duplicated state tracking for chatgpt.	1 year ago
Adam Treat	7d2ce06029	Start working on more thread safety and model load error handling.	1 year ago
Adam Treat	d5f56d3308	Forgot to add a signal handler.	1 year ago
Adam Treat	aa2c824258	Initialize these.	1 year ago
Adam Treat	d018b4c821	Make this atomic.	1 year ago
Adam Treat	a3a6a20146	Don't store db results in ChatLLM.	1 year ago
Adam Treat	0cfe225506	Remove this as unnecessary.	1 year ago
Adam Treat	7c28e79644	Fix regenerate response with references.	1 year ago
AT	f76df0deac	Typescript (#1022) ... * Show token generation speed in gui. * Add typescript/javascript to list of highlighted languages.	1 year ago
AT	2b6cc99a31	Show token generation speed in gui. (#1020)	1 year ago
cosmic-snow	fd419caa55	Minor models.json description corrections. (#1013) ... Signed-off-by: cosmic-snow <134004613+cosmic-snow@users.noreply.github.com>	1 year ago
Adam Treat	42e8049564	Bump version and new release notes for metal bugfix edition.	1 year ago
Adam Treat	e2c807d4df	Always install metal on apple.	1 year ago
Adam Treat	d5179ac0c0	Fix cmake build.	1 year ago
Adam Treat	d4283c0053	Fix metal and replit.	1 year ago
Adam Treat	0a0d4a714e	New release and bump the version.	1 year ago
Adam Treat	782e1e77a4	Fix up model names that don't begin with 'ggml-'	1 year ago
Adam Treat	b39a7d4fd9	Fix json.	1 year 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.	1 year 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.	1 year ago
Adam Treat	8953b7f6a6	Fix regression in checked of db and network.	1 year 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)	1 year ago
Adam Treat	68ff7001ad	Bugfixes for prompt syntax highlighting.	1 year ago
Adam Treat	60d95cdd9b	Fix some bugs with bash syntax and add some C23 keywords.	1 year ago
Adam Treat	e986f18904	Add c++/c highighting support.	1 year ago
Adam Treat	ae46234261	Spelling error.	1 year ago
Adam Treat	318c51c141	Add code blocks and python syntax highlighting.	1 year ago
Adam Treat	b67cba19f0	Don't interfere with selection.	1 year ago
Adam Treat	50c5b82e57	Clean up the context links a bit.	1 year 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.	1 year 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>	1 year ago
Adam Treat	b162b5c64e	Revert "llama on Metal (#885)" ... This reverts commit c55f81b860.	1 year 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>	1 year ago
pingpongching	0d0fae0ca8	Change the default values for generation in GUI	1 year ago
Adam Treat	8fb73c2114	Forgot to bump.	1 year ago
Richard Guo	be2310322f	update models json with replit model	1 year ago