343 Commits (dfe85386b5a2e38ae438c5884b97a82dde77d341)

 

All Branches   

Search

Author	SHA1	Message	Date
Adam Treat	993a43d33a	Minor cleanup.	1 year ago
Adam Treat	cca2a88e47	Getting ready for next update.	1 year ago
Adam Treat	bec8072fe1	Fix logic.	1 year ago
eachadea	116f740fb5	Don't build test_hw on apple silicon	1 year ago
Adam Treat	3e7cf346d6	Restore basic functionality.	1 year ago
Adam Treat	670bbe4db5	Make the settings dialog persist across sessions.	1 year ago
Adam Treat	294f2d6041	Revamp hardware tester to print to stdout the result in single word.	1 year ago
Adam Treat	e4d75cbfcd	Remove this as clang does not support.	1 year ago
AT	6f1fe51087	Update README.md	1 year ago
Adam Treat	14831cd1c0	Add a small program that tests hardware.	1 year ago
AT	2dc26cfd09	Update README.md	1 year ago
Adam Treat	4d26f5daeb	Silence a warning now that we're forked.	1 year ago
Adam Treat	442ca09b32	Remove ggml submodule in favor of llama.cpp	1 year ago
Adam Treat	bb78ee0025	Back out the prompt/response finding in gptj since it doesn't seem to help. ... Guard against reaching the end of the context window which we don't handle gracefully except for avoiding a crash.	1 year ago
Tom Jobbins	154f35ce53	Update HTTP link to model to point to the latest Jazzy model (in the CLI-only build section) (#78)	1 year ago
Adam Treat	65abaa19e5	Fix warning and update llama.cpp submodule to latest.	1 year ago
Adam Treat	51768bfbda	Use default params unless we override them.	1 year ago
Adam Treat	b15feb5a4c	Crop the filename.	1 year ago
Adam Treat	5a00c83139	Display filesize info in the model downloader.	1 year ago
Adam Treat	cd5f525950	Add multi-line prompt support.	1 year ago
Adam Treat	4c970fdc9c	Pin the llama.cpp to a slightly older version.	1 year ago
Adam Treat	43e6d05d21	Don't crash starting with no model.	1 year ago
Adam Treat	d336db9fe9	Don't use versions for model downloader.	1 year ago
eachadea	b09ca009c5	Don't build a universal binary ... unless -DBUILD_UNIVERSAL=ON	1 year ago
Adam Treat	55084333a9	Add llama.cpp support for loading llama based models in the gui. We now ... support loading both gptj derived models and llama derived models.	1 year ago
Aaron Miller	f1b87d0b56	Add thread count setting	1 year ago
Adam Treat	e6cb6a2ae3	Add a new model download feature.	1 year ago
Adam Treat	1eda8f030e	Allow unloading/loading/changing of models.	1 year ago
Aaron Miller	3a82a1d96c	remove fill color for prompt template box	1 year ago
Adam Treat	a842f6c33f	Fix link color to have consistency across platforms.	1 year ago
Adam Treat	0928c01ddb	Make the gui accessible.	1 year ago
Pavol Rusnak	0e599e6b8a	readme: GPL -> MIT license	1 year ago
Adam Treat	ef711b305b	Changing to MIT license.	1 year ago
Adam Treat	bbf838354e	Don't add version number to the installer or the install location.	1 year ago
Adam Treat	9f4e3cb7f4	Bump the version for the context bug fix.	1 year ago
Adam Treat	15ae0a4441	Fix the context.	1 year ago
Adam Treat	801107a12c	Set a new default temp that is more conservative.	1 year ago
AT	ea7179e2e8	Update README.md	1 year ago
Adam Treat	7dbf81ed8f	Update submodule.	1 year ago
Adam Treat	42fb215f61	Bump version to 2.1 as this has been referred to far and wide as ... GPT4All v2 so doing this to decrease confusion. Also, making the version number visible in the title bar.	1 year ago
Adam Treat	1dcd4dce58	Update the bundled model name.	1 year ago
Adam Treat	7ea548736b	New version.	1 year ago
Adam Treat	659ab13665	Don't allow empty prompts. Context past always equal or greater than zero.	1 year ago
Adam Treat	7e9ca06366	Trim trailing whitespace at the end of generation.	1 year ago
Adam Treat	fdf7f20d90	Remove newlines too.	1 year ago
Adam Treat	f8b962d50a	More conservative default params and trim leading whitespace from response.	1 year ago
TheBloke	7215b9f3fb	Change the example CLI prompt to something more appropriate, as this is not a Llama model! :)	1 year ago
TheBloke	16f6b04a47	Fix repo name	1 year ago
TheBloke	67fcfeea8b	Update README to include instructions for building CLI only ... Users may want to play around with gpt4all-j from the command line. But they may not have Qt, and might not want to get it, or may find it very hard to do so - eg when using a Google Colab or similar hosted service. It's easy to build the CLI tools just by building the `ggml` sub folder. So this commit adds instructions on doing that, including an example invocation of the `gpt-j` binary.	1 year ago
TheBloke	605b3d18ad	Update .gitignore to ignore a local `build` directory.	1 year ago