Commit Graph

46 Commits

Author SHA1 Message Date
Adam Treat
8eb0844277 Check if the trimmed version is empty. 2023-07-12 14:31:43 -04:00
Adam Treat
be395c12cc Make all system prompts empty by default if model does not include in training data. 2023-07-12 14:31:43 -04:00
Adam Treat
34a3b9c857 Don't block on exit when not connected. 2023-07-11 12:37:21 -04:00
Adam Treat
88bbe30952 Provide a guardrail for OOM errors. 2023-07-11 12:09:33 -04:00
Adam Treat
99cd555743 Provide some guardrails for thread count. 2023-07-10 17:29:51 -04:00
Adam Treat
3e3b05a2a4 Don't process the system prompt when restoring state. 2023-07-10 16:20:19 -04:00
Adam Treat
12083fcdeb When deleting chats we sometimes have to update our modelinfo. 2023-07-09 14:52:08 -04:00
Adam Treat
59f3c093cb Stop generating anything on shutdown. 2023-07-09 14:42:11 -04:00
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.
2023-07-05 15:51:42 -04:00
Adam Treat
7f252b4970 This completes the work of consolidating all settings that can be changed by the user on new settings object. 2023-06-29 00:44:48 -03:00
Adam Treat
267601d670 Enable the force metal setting. 2023-06-27 14:23:56 -03:00
Aaron Miller
e22dd164d8 add falcon to chatllm::serialize 2023-06-27 14:06:39 -03:00
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
2023-06-27 14:06:39 -03:00
Adam Treat
7f01b153b3 Modellist temp 2023-06-26 14:14:46 -04:00
Adam Treat
c8a590bc6f Get rid of last blocking operations and make the chat/llm thread safe. 2023-06-20 18:18:10 -03:00
Adam Treat
84ec4311e9 Remove duplicated state tracking for chatgpt. 2023-06-20 18:18:10 -03:00
Adam Treat
7d2ce06029 Start working on more thread safety and model load error handling. 2023-06-20 14:39:22 -03:00
Adam Treat
aa2c824258 Initialize these. 2023-06-19 15:38:01 -07:00
Adam Treat
a3a6a20146 Don't store db results in ChatLLM. 2023-06-19 15:38:01 -07:00
Adam Treat
0cfe225506 Remove this as unnecessary. 2023-06-19 15:38:01 -07:00
AT
2b6cc99a31
Show token generation speed in gui. (#1020) 2023-06-19 14:34:53 -04:00
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.
2023-06-16 11:09:33 -04:00
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
2023-06-06 17:09:00 -04:00
Andriy Mulyar
d8e821134e
Revert "Fix bug with resetting context with chatgpt model." (#859)
This reverts commit 031d7149a7.
2023-06-05 14:25:37 -04:00
Adam Treat
9f590db98d Better error handling when the model fails to load. 2023-06-04 14:55:05 -04:00
niansa/tuxifan
f3564ac6b9
Fixed tons of warnings and clazy findings (#811) 2023-06-02 15:46:41 -04:00
Adam Treat
031d7149a7 Fix bug with resetting context with chatgpt model. 2023-06-01 17:34:13 -04:00
Adam Treat
aea94f756d Better name for database results. 2023-06-01 17:14:17 -04:00
Adam Treat
f62e439a2d Make localdocs work with server mode. 2023-06-01 17:14:17 -04:00
Adam Treat
f74363bb3a Fix compile 2023-06-01 10:58:31 -04:00
niansa
a3d08cdcd5 Dlopen better implementation management (Version 2) 2023-06-01 07:44:15 -04:00
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.
2023-05-31 17:04:01 -04:00
Adam Treat
912cb2a842 Get rid of blocking behavior for regenerate response. 2023-05-30 18:17:59 -04:00
Adam Treat
c800291e7f Add prompt processing and localdocs to the busy indicator in UI. 2023-05-25 11:28:06 -04:00
Adam Treat
618895f0a1 Turn off the debugging messages by default. 2023-05-25 11:28:06 -04:00
Adam Treat
7e42af5f33 localdocs 2023-05-25 11:28:06 -04:00
Adam Treat
748e7977ca Generate the new prompt/response pair before model loading in server mode. 2023-05-16 10:31:55 -04:00
Adam Treat
f931de21c5 Add save/restore to chatgpt chats and allow serialize/deseralize from disk. 2023-05-16 10:31:55 -04:00
Adam Treat
0cd509d530 Add large network icon background for chatgpt and server modes. 2023-05-16 10:31:55 -04:00
Adam Treat
dd27c10f54 Preliminary support for chatgpt models. 2023-05-16 10:31:55 -04:00
Adam Treat
b71c0ac3bd The server has different lifetime mgmt than the other chats. 2023-05-13 19:34:54 -04:00
Adam Treat
ddc24acf33 Much better memory mgmt for multi-threaded model loading/unloading. 2023-05-13 19:10:56 -04:00
Adam Treat
2989b74d43 httpserver 2023-05-13 19:07:06 -04:00
Adam Treat
76675536b0 Cleanup the chatllm properly. 2023-05-12 17:11:52 -04:00
Adam Treat
d918b02c29 Move the llmodel C API to new top-level directory and version it. 2023-05-10 11:46:40 -04:00
Adam Treat
6015154bef Moving everything to subdir for monorepo merge. 2023-05-10 10:26:55 -04:00