Adam Treat
01e582f15b
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
02c9bb4ac7
Restore the model when switching chats.
2023-05-03 12:45:14 -04:00
Adam Treat
078675386f
Experiment with a much shorter default prompt template.
2023-05-03 12:19:14 -04:00
Adam Treat
97ec9074e5
Add reverse prompts for llama models.
2023-05-03 11:58:26 -04:00
Adam Treat
fec5093351
Don't exceed the window size for dialogs.
2023-05-03 08:37:45 -04:00
Adam Treat
005898b1bc
Changes the datalake feature so all conversations are captured when opted-in.
2023-05-03 07:54:45 -04:00
Aaron Miller
f487118007
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
db094c5b92
More extensive usage stats to help diagnose errors and problems in the ui.
2023-05-02 20:31:17 -04:00
Adam Treat
f8c3ae6cc7
Some more startup info to help determine what hardware we need to support.
2023-05-02 16:24:06 -04:00
Adam Treat
a7c02a52ca
Don't block the GUI when reloading via combobox.
2023-05-02 15:02:25 -04:00
Adam Treat
745a8c3ac5
Provide a confirm button for deletion of chats.
2023-05-02 12:36:21 -04:00
Adam Treat
60acc18625
Use different border colors if we're current or being edited.
2023-05-02 11:34:39 -04:00
Adam Treat
6a905d38d9
Update the right index when removing.
2023-05-02 11:26:21 -04:00
Adam Treat
c217b7538a
Generate names via llm.
2023-05-02 11:19:17 -04:00
Zach Nussbaum
d1ec122079
Merge pull request #472 from berkantay/main
...
Update README.md
2023-05-02 10:15:40 -04:00
Adam Treat
1e6e682156
Always have a chat.
2023-05-02 09:07:28 -04:00
Adam Treat
c3d923cdc7
Don't add new chats willy nilly.
2023-05-02 07:53:09 -04:00
Adam Treat
548e68ee0c
Allow removing chats.
2023-05-01 20:56:53 -04:00
Adam Treat
d91dd567e2
Hot swapping of conversations. Destroys context for now.
2023-05-01 20:27:07 -04:00
Adam Treat
925ad70833
Turn the chat list into a model.
2023-05-01 17:13:20 -04:00
Richard Guo
424b680b42
rough draft of monorepo plan
2023-05-01 15:45:39 -04:00
Richard Guo
6304f6d322
mono repo structure
2023-05-01 15:45:23 -04:00
Adam Treat
463c1474dc
Provide convenience methods for adding/removing/changing chat.
2023-05-01 14:24:16 -04:00
Adam Treat
1b1c3f6333
Break out the drawer into own component.
2023-05-01 13:51:46 -04:00
Adam Treat
482f543675
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
8b94a23253
Continue to shrink the API space for qml and the backend.
2023-05-01 12:30:54 -04:00
Adam Treat
385743b302
Consolidate these into single api from qml to backend.
2023-05-01 12:24:51 -04:00
Adam Treat
414a12c33d
Major refactor in prep for multiple conversations.
2023-05-01 09:10:05 -04:00
Adam Treat
75c8bf28a1
Move the reset and id into the chat object.
2023-04-30 21:05:54 -04:00
Adam Treat
bbffa7364b
Add new C++ version of the chat model. Getting ready for chat history.
2023-04-30 20:28:43 -04:00
AT
83609bf8a5
Update README.md
2023-04-30 16:07:59 -04:00
AT
5bf8d48b3b
Update README.md
2023-04-30 09:05:26 -04:00
AT
40fe88f6ca
Update README.md
2023-04-30 08:54:45 -04:00
Adam Treat
037a9a6ec5
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
0f195eae48
Update README.md
2023-04-30 07:07:22 -04:00
AT
c2de4ebb7a
Update README.md
2023-04-30 07:02:01 -04:00
Adam Treat
08b38bb4d2
Bump the version.
2023-04-29 21:04:47 -04:00
Adam Treat
9b467f2dee
Use the universal sep.
2023-04-29 21:03:10 -04:00
Berkant
183b1e6c85
Update README.md
...
README.md typo fix.
2023-04-30 01:07:14 +03:00
AT
5d7d5d2a74
Update README.md
2023-04-29 17:49:18 -04:00
AT
ac6c3dea61
Update README.md
2023-04-29 17:48:00 -04:00
Adam Treat
ae17598a51
Make an offline installer option.
2023-04-29 12:13:11 -04:00
Adam Treat
cd41eb3280
Don't attempt to send shutdown which won't work anyway.
2023-04-29 11:07:14 -04:00
Adam Treat
869175bc06
Send optout for real and only once.
2023-04-29 11:05:44 -04:00
Adam Treat
34407f1563
Don't set the app version in the llmodel.
2023-04-29 10:31:12 -04:00
Adam Treat
1f3d4e487f
Bump the version.
2023-04-29 08:56:53 -04:00
Adam Treat
f70a549975
New version of icns made on a mac.
2023-04-29 08:40:54 -04:00
Adam Treat
6d0bae5362
Add 1024 resolution to icns.
2023-04-29 04:39:55 -04:00
Adam Treat
2e21fb9c81
Fixup icns
2023-04-29 04:38:36 -04:00
Adam Treat
7d0970cbe2
Rework the icon a bit to more closely match macOS style guidelines.
2023-04-29 04:31:06 -04:00
