64 Commits (2eb83b9f2a4762898d8d16b57d6388f3ec10b03d)

Author	SHA1	Message	Date
Cebtenzzre	2eb83b9f2a	chat: report reason for fallback to CPU	1 year ago
Adam Treat	12f943e966	Fix regenerate button to be deterministic and bump the llama version to latest we have for gguf.	1 year ago
Cebtenzzre	a49a1dcdf4	chatllm: grammar fix	1 year ago
Cebtenzzre	8f3abb37ca	fix references to removed model types	1 year ago
Adam Treat	d90d003a1d	Latest rebase on llama.cpp with gguf support.	1 year ago
Adam Treat	045f6e6cdc	Link against ggml in bin so we can get the available devices without loading a model.	1 year ago
Adam Treat	aa33419c6e	Fallback to CPU more robustly.	1 year ago
Adam Treat	3076e0bf26	Only show GPU when we're actually using it.	1 year ago
Adam Treat	1fa67a585c	Report the actual device we're using.	1 year ago
Adam Treat	21a3244645	Fix a bug where we're not properly falling back to CPU.	1 year ago
Aaron Miller	6f038c136b	init at most one vulkan device, submodule update ... fixes issues w/ multiple of the same gpu	1 year ago
Adam Treat	891ddafc33	When device is Auto (the default) then we will only consider discrete GPU's otherwise fallback to CPU.	1 year ago
Adam Treat	8f99dca70f	Bring the vulkan backend to the GUI.	1 year ago
Adam Treat	987546c63b	Nomic vulkan backend licensed under the Software for Open Models License (SOM), version 1.0.	1 year ago
Adam Treat	6d03b3e500	Add starcoder support.	1 year ago
Adam Treat	0efdbfcffe	Bert	1 year ago
Adam Treat	315a1f2aa2	Move it back as internal class.	1 year ago
Adam Treat	1f749d7633	Clean up backend code a bit and hide impl. details.	1 year ago
Adam Treat	8eb0844277	Check if the trimmed version is empty.	1 year ago
Adam Treat	be395c12cc	Make all system prompts empty by default if model does not include in training data.	1 year ago
Adam Treat	34a3b9c857	Don't block on exit when not connected.	1 year ago
Adam Treat	88bbe30952	Provide a guardrail for OOM errors.	1 year ago
Adam Treat	99cd555743	Provide some guardrails for thread count.	1 year ago
Adam Treat	3e3b05a2a4	Don't process the system prompt when restoring state.	1 year ago
Adam Treat	12083fcdeb	When deleting chats we sometimes have to update our modelinfo.	1 year ago
Adam Treat	59f3c093cb	Stop generating anything on shutdown.	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	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	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	7f01b153b3	Modellist temp	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	aa2c824258	Initialize these.	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
AT	2b6cc99a31	Show token generation speed in gui. (#1020)	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
Richard Guo	c4706d0c14	Replit Model (#713) ... * porting over replit code model to gpt4all * replaced memory with kv_self struct * continuing debug * welp it built but lot of sus things * working model loading and somewhat working generate.. need to format response? * revert back to semi working version * finally got rid of weird formatting * figured out problem is with python bindings - this is good to go for testing * addressing PR feedback * output refactor * fixed prompt reponse collection * cleanup * addressing PR comments * building replit backend with new ggmlver code * chatllm replit and clean python files * cleanup * updated replit to match new llmodel api * match llmodel api and change size_t to Token * resolve PR comments * replit model commit comment	1 year ago
Andriy Mulyar	d8e821134e	Revert "Fix bug with resetting context with chatgpt model." (#859) ... This reverts commit 031d7149a7.	1 year ago
Adam Treat	9f590db98d	Better error handling when the model fails to load.	1 year ago
niansa/tuxifan	f3564ac6b9	Fixed tons of warnings and clazy findings (#811)	1 year ago
Adam Treat	031d7149a7	Fix bug with resetting context with chatgpt model.	1 year ago
Adam Treat	aea94f756d	Better name for database results.	1 year ago
Adam Treat	f62e439a2d	Make localdocs work with server mode.	1 year ago
Adam Treat	f74363bb3a	Fix compile	1 year ago
niansa	a3d08cdcd5	Dlopen better implementation management (Version 2)	1 year ago
AT	48275d0dcc	Dlopen backend 5 (#779) ... Major change to the backend that allows for pluggable versions of llama.cpp/ggml. This was squashed merged from dlopen_backend_5 where the history is preserved.	1 year ago