1463 Commits (7a190473292604734f02f1a347020ab4f44a4617)

 

All Branches   

Search

Author	SHA1	Message	Date
cebtenzzre	7a19047329	llmodel: do not call magic_match unless build variant is correct (#1488)	9 months ago
Adam Treat	df8528df73	Another codespell attempted fix.	9 months ago
Adam Treat	f0742c22f4	Restore state from text if necessary.	9 months ago
Adam Treat	35f9cdb70a	Do not delete saved chats if we fail to serialize properly.	9 months ago
cebtenzzre	9fb135e020	cmake: install the GPT-J plugin (#1487)	9 months ago
Cebtenzzre	df66226f7d	issue template: remove "Related Components" section	9 months ago
Aaron Miller	3c25d81759	make codespell happy	9 months ago
Jan Philipp Harries	4f0cee9330	added EM German Mistral Model	9 months ago
Adam Treat	56c0d2898d	Update the language here to avoid misunderstanding.	9 months ago
Adam Treat	b2cd3bdb3f	Fix crasher with an empty string for prompt template.	9 months ago
Cebtenzzre	5fe685427a	chat: clearer CPU fallback messages	9 months ago
Adam Treat	eec906aa05	Speculative fix for build on mac.	9 months ago
Aaron Miller	9325075f80	fix stray comma in models2.json ... Signed-off-by: Aaron Miller <apage43@ninjawhale.com>	9 months ago
Adam Treat	a9acdd25de	Push a new version number for llmodel backend now that it is based on gguf.	9 months ago
Adam Treat	f028f67c68	Add starcoder, rift and sbert to our models2.json.	9 months ago
Aaron Miller	a10f3aea5e	python/embed4all: use gguf model, allow passing kwargs/overriding model	9 months ago
Cebtenzzre	8bb6a6c201	rebase on newer llama.cpp	9 months ago
Adam Treat	4528f73479	Reorder and refresh our models2.json.	9 months ago
Cebtenzzre	d87573ea75	remove old llama.cpp submodules	9 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	9 months ago
Adam Treat	f605a5b686	Add q8_0 kernels to kompute shaders and bump to latest llama/gguf.	9 months ago
Cebtenzzre	1534df3e9f	backend: do not use Vulkan with non-LLaMA models	9 months ago
Cebtenzzre	672cb850f9	differentiate between init failure and unsupported models	9 months ago
Cebtenzzre	a5b93cf095	more accurate fallback descriptions	9 months ago
Cebtenzzre	75deee9adb	chat: make sure to clear fallback reason on success	9 months ago
Cebtenzzre	2eb83b9f2a	chat: report reason for fallback to CPU	9 months ago
Adam Treat	906699e8e9	Bump to latest llama/gguf branch.	9 months ago
Adam Treat	ea66669cef	Switch to new models2.json for new gguf release and bump our version to ... 2.5.0.	9 months ago
Cebtenzzre	088afada49	llamamodel: fix static vector in LLamaModel::endTokens	9 months ago
Adam Treat	b4d82ea289	Bump to the latest fixes for vulkan in llama.	9 months ago
Adam Treat	12f943e966	Fix regenerate button to be deterministic and bump the llama version to latest we have for gguf.	9 months ago
Cebtenzzre	40c78d2f78	python binding: print debug message to stderr	9 months ago
Adam Treat	5d346e13d7	Add q6_k kernels for vulkan.	9 months ago
Adam Treat	4eefd386d0	Refactor for subgroups on mat * vec kernel.	9 months ago
Cebtenzzre	3c2aa299d8	gptj: remove unused variables	9 months ago
Cebtenzzre	f9deb87d20	convert scripts: add feed-forward length for better compatiblilty ... This GGUF key is used by all llama.cpp models with upstream support.	9 months ago
Cebtenzzre	cc7675d432	convert scripts: make gptj script executable	9 months ago
Cebtenzzre	0493e6eb07	convert scripts: use bytes_to_unicode from transformers	9 months ago
Cebtenzzre	a49a1dcdf4	chatllm: grammar fix	9 months ago
Cebtenzzre	d5d72f0361	gpt-j: update inference to match latest llama.cpp insights ... - Use F16 KV cache - Store transposed V in the cache - Avoid unnecessary Q copy Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> ggml upstream commit 0265f0813492602fec0e1159fe61de1bf0ccaf78	9 months ago
Cebtenzzre	050e7f076e	backend: port GPT-J to GGUF	9 months ago
Cebtenzzre	31b20f093a	modellist: fix the system prompt	9 months ago
Cebtenzzre	8f3abb37ca	fix references to removed model types	9 months ago
Cebtenzzre	4219c0e2e7	convert scripts: make them directly executable	9 months ago
Cebtenzzre	ce7be1db48	backend: use llamamodel.cpp for Falcon	9 months ago
Cebtenzzre	cca9e6ce81	convert_mpt_hf_to_gguf.py: better tokenizer decoding	9 months ago
Cebtenzzre	25297786db	convert scripts: load model as late as possible	9 months ago
Cebtenzzre	fd47088f2b	conversion scripts: cleanup	9 months ago
Cebtenzzre	6277eac9cc	backend: use llamamodel.cpp for StarCoder	9 months ago
Cebtenzzre	aa706ab1ff	backend: use gguf branch of llama.cpp-mainline	9 months ago