1690 Commits (08b5dc8598b9511dda0d0c7f7783783bd818a627)

 

All Branches   

Search

Author	SHA1	Message	Date
cebtenzzre	245c5ce5ea	update default model URLs (#1538)	11 months ago
cebtenzzre	4338e72a51	MPT: use upstream llama.cpp implementation (#1515)	11 months ago
cebtenzzre	0fe2e19691	llamamodel: re-enable error messages by default (#1537)	11 months ago
cebtenzzre	f505619c84	README: remove star history (#1536)	11 months ago
cebtenzzre	5fbeeb1cb4	python: connection resume and MSVC support (#1535)	11 months ago
cebtenzzre	017c3a9649	python: prepare version 2.0.0rc1 (#1529)	11 months ago
cebtenzzre	bcbcad98d0	CI: increase minimum macOS version of Python bindings to 10.15 (#1511)	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
cebtenzzre	9a19c740ee	kompute: fix library loading issues with kp_logger (#1517)	11 months ago
Aaron Miller	f79557d2aa	speedup: just use mat*vec shaders for mat*mat ... so far my from-scratch mat*mats are still slower than just running more invocations of the existing Metal ported mat*vec shaders - it should be theoretically possible to make a mat*mat that's faster (for actual mat*mat cases) than an optimal mat*vec, but it will need to be at *least* as fast as the mat*vec op and then take special care to be cache-friendly and save memory bandwidth, as the # of compute ops is the same	11 months ago
cebtenzzre	22de3c56bd	convert scripts: fix AutoConfig typo (#1512)	11 months ago
Aaron Miller	10f9b49313	update mini-orca 3b to gguf2, license ... Signed-off-by: Aaron Miller <apage43@ninjawhale.com>	11 months ago
Aaron Miller	2490977f89	q6k, q4_1 mat*mat	11 months ago
niansa/tuxifan	a35f1ab784	Updated chat wishlist (#1351)	11 months ago
cebtenzzre	4d4275d1b8	python: replace deprecated pkg_resources with importlib (#1505)	11 months ago
Alex Soto	3c45a555e9	Improves Java API signatures maintaining back compatibility	11 months ago
Aaron Miller	f39df0906e	fix embed4all filename ... https://discordapp.com/channels/1076964370942267462/1093558720690143283/1161778216462192692 Signed-off-by: Aaron Miller <apage43@ninjawhale.com>	11 months ago
umarmnaq	005c092943	Update README.md ... Signed-off-by: umarmnaq <102142660+umarmnaq@users.noreply.github.com>	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	aed2068342	python: always check status code of HTTP responses (#1502)	11 months ago
Aaron Miller	afaa291eab	python bindings should be quiet by default ... * disable llama.cpp logging unless GPT4ALL_VERBOSE_LLAMACPP envvar is nonempty * make verbose flag for retrieve_model default false (but also be overridable via gpt4all constructor) should be able to run a basic test: ```python import gpt4all model = gpt4all.GPT4All('/Users/aaron/Downloads/rift-coder-v0-7b-q4_0.gguf') print(model.generate('def fib(n):')) ``` and see no non-model output when successful	11 months ago
cebtenzzre	7b611b49f2	llmodel: print an error if the CPU does not support AVX (#1499)	11 months ago
cebtenzzre	f81b4b45bf	python: support Path in GPT4All.__init__ (#1462)	11 months ago
Aaron Miller	043617168e	do not process prompts on gpu yet	11 months ago
Aaron Miller	64001a480a	mat*mat for q4_0, q8_0	11 months ago
cebtenzzre	04499d1c7d	chatllm: do not write uninitialized data to stream (#1486)	12 months ago
cebtenzzre	7a19047329	llmodel: do not call magic_match unless build variant is correct (#1488)	12 months ago
Adam Treat	df8528df73	Another codespell attempted fix.	12 months ago
Adam Treat	f0742c22f4	Restore state from text if necessary.	12 months ago
Adam Treat	35f9cdb70a	Do not delete saved chats if we fail to serialize properly.	12 months ago
cebtenzzre	9fb135e020	cmake: install the GPT-J plugin (#1487)	12 months ago
Cebtenzzre	df66226f7d	issue template: remove "Related Components" section	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
Adam Treat	eec906aa05	Speculative fix for build on mac.	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	a9acdd25de	Push a new version number for llmodel backend now that it is based on gguf.	12 months ago
Adam Treat	f028f67c68	Add starcoder, rift and sbert to our models2.json.	12 months ago
Aaron Miller	a10f3aea5e	python/embed4all: use gguf model, allow passing kwargs/overriding model	12 months ago
Cebtenzzre	8bb6a6c201	rebase on newer llama.cpp	12 months ago
Adam Treat	4528f73479	Reorder and refresh our models2.json.	12 months ago
Cebtenzzre	d87573ea75	remove old llama.cpp submodules	12 months ago
Cebtenzzre	cc6db61c93	backend: fix build with Visual Studio generator ... Use the $<CONFIG> generator expression instead of CMAKE_BUILD_TYPE. This is needed because Visual Studio is a multi-configuration generator, so we do not know what the build type will be until `cmake --build` is called. Fixes #1470	12 months ago
Adam Treat	f605a5b686	Add q8_0 kernels to kompute shaders and bump to latest llama/gguf.	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