Adam Treat
8d2c8c8cb0
Turn off saving chats to disk by default as it eats so much disk space.
2023-05-05 12:30:11 -04:00
Adam Treat
6d4d86d07c
Bump the version.
2023-05-05 11:43:25 -04:00
Adam Treat
d0d5d84e06
Add reverse prompt support for gptj too.
2023-05-05 11:16:24 -04:00
Adam Treat
06bb6960d4
Add about dialog.
2023-05-05 10:47:05 -04:00
Adam Treat
659442394f
Persistent state for gpt-j models too.
2023-05-05 10:00:17 -04:00
Adam Treat
5b71d39024
Don't crash if state has not been set.
2023-05-05 10:00:17 -04:00
Aaron Miller
019f6d0103
include <cstdint> in llmodel.h
2023-05-04 20:36:19 -04:00
Adam Treat
f291853e51
First attempt at providing a persistent chat list experience.
...
Limitations:
1) Context is not restored for gpt-j models
2) When you switch between different model types in an existing chat
the context and all the conversation is lost
3) The settings are not chat or conversation specific
4) The sizes of the chat persisted files are very large due to how much
data the llama.cpp backend tries to persist. Need to investigate how
we can shrink this.
2023-05-04 15:31:41 -04:00
Adam Treat
081d32bd97
Restore the model when switching chats.
2023-05-03 12:45:14 -04:00
Adam Treat
0bb52fc5fe
Experiment with a much shorter default prompt template.
2023-05-03 12:19:14 -04:00
Adam Treat
82c1d08b33
Add reverse prompts for llama models.
2023-05-03 11:58:26 -04:00
Adam Treat
01accf9e33
Don't exceed the window size for dialogs.
2023-05-03 08:37:45 -04:00
Adam Treat
0f70289ba4
Changes the datalake feature so all conversations are captured when opted-in.
2023-05-03 07:54:45 -04:00
Aaron Miller
edad3baa99
download: make model downloads resumable
...
* save files as `incomplete-{filename}` in the dest folder
* rename into place after hash is confirmed or delete if hash is bad
* resume downloads using http `range`
* if DL is resumed from a different app session rewind a bit -
this is to deal with the case where the file size changes before
the content is fully flushed out
* flush dest file at end of readyRead, this mitigates the above
and provides backpressure on the download if the destination disk
is slower than the network connection
2023-05-02 20:36:25 -04:00
Adam Treat
4a09f0f0ec
More extensive usage stats to help diagnose errors and problems in the ui.
2023-05-02 20:31:17 -04:00
Adam Treat
cb085a6418
Some more startup info to help determine what hardware we need to support.
2023-05-02 16:24:06 -04:00
Adam Treat
21dc522200
Don't block the GUI when reloading via combobox.
2023-05-02 15:02:25 -04:00
Adam Treat
48837a62fa
Provide a confirm button for deletion of chats.
2023-05-02 12:36:21 -04:00
Adam Treat
bb3e08e3dd
Use different border colors if we're current or being edited.
2023-05-02 11:34:39 -04:00
Adam Treat
f4f27fc38f
Update the right index when removing.
2023-05-02 11:26:21 -04:00
Adam Treat
f13f4f4700
Generate names via llm.
2023-05-02 11:19:17 -04:00
Adam Treat
a62fafc308
Always have a chat.
2023-05-02 09:07:28 -04:00
Adam Treat
86132cfc8b
Don't add new chats willy nilly.
2023-05-02 07:53:09 -04:00
Adam Treat
118e0bdc44
Allow removing chats.
2023-05-01 20:56:53 -04:00
Adam Treat
412cad99f2
Hot swapping of conversations. Destroys context for now.
2023-05-01 20:27:07 -04:00
Adam Treat
a48226613c
Turn the chat list into a model.
2023-05-01 17:13:20 -04:00
Adam Treat
679b61ee07
Provide convenience methods for adding/removing/changing chat.
2023-05-01 14:24:16 -04:00
Adam Treat
8f80f8e3a2
Break out the drawer into own component.
2023-05-01 13:51:46 -04:00
Adam Treat
6e6b96375d
Handle the fwd of important signals from LLM object so qml doesn't have to deal with which chat is current.
2023-05-01 12:41:03 -04:00
Adam Treat
c0d4a9d426
Continue to shrink the API space for qml and the backend.
2023-05-01 12:30:54 -04:00
Adam Treat
ed59190e48
Consolidate these into single api from qml to backend.
2023-05-01 12:24:51 -04:00
Adam Treat
4d87c46948
Major refactor in prep for multiple conversations.
2023-05-01 09:10:05 -04:00
Adam Treat
e005ab8c0a
Move the reset and id into the chat object.
2023-04-30 21:05:54 -04:00
Adam Treat
d1e3198b65
Add new C++ version of the chat model. Getting ready for chat history.
2023-04-30 20:28:43 -04:00
AT
65d4b8a886
Update README.md
2023-04-30 16:07:59 -04:00
AT
d3d8229b04
Update README.md
2023-04-30 09:05:26 -04:00
AT
8e696bb4e4
Update README.md
2023-04-30 08:54:45 -04:00
Adam Treat
9f323759ce
Remove these as it is mitigated by repeat penalty and models really should train this out.
2023-04-30 08:02:39 -04:00
AT
ef2e1bd4fe
Update README.md
2023-04-30 07:07:22 -04:00
AT
f37e9f9039
Update README.md
2023-04-30 07:02:01 -04:00
Adam Treat
13401fc52f
Bump the version.
2023-04-29 21:04:47 -04:00
Adam Treat
a6ca45c9dd
Use the universal sep.
2023-04-29 21:03:10 -04:00
AT
573e4e1f73
Update README.md
2023-04-29 17:49:18 -04:00
AT
84ffd801ec
Update README.md
2023-04-29 17:48:00 -04:00
Adam Treat
727a74de6c
Make an offline installer option.
2023-04-29 12:13:11 -04:00
Adam Treat
c4d312ae11
Don't attempt to send shutdown which won't work anyway.
2023-04-29 11:07:14 -04:00
Adam Treat
8aed93daa5
Send optout for real and only once.
2023-04-29 11:05:44 -04:00
Adam Treat
8fe60c29fb
Don't set the app version in the llmodel.
2023-04-29 10:31:12 -04:00
Adam Treat
9ebf2537fa
Bump the version.
2023-04-29 08:56:53 -04:00
Adam Treat
3cf8f0da13
New version of icns made on a mac.
2023-04-29 08:40:54 -04:00
