Adam Treat
6d943917f1
Fail early/gracefully if incompatible hardware detected. And default to universal builds on mac.
2023-05-08 08:23:00 -04:00
Adam Treat
ab13148430
The GUI should come up immediately and not wait on deserializing from disk.
2023-05-06 20:01:14 -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
86132cfc8b
Don't add new chats willy nilly.
2023-05-02 07:53:09 -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
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
4d87c46948
Major refactor in prep for multiple conversations.
2023-05-01 09:10:05 -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
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
Adam Treat
a6ca45c9dd
Use the universal sep.
2023-04-29 21:03:10 -04:00
Adam Treat
69f92d8ea8
Load models from filepath only.
2023-04-28 20:15:10 -04:00
Adam Treat
62a885de40
Always try and load default model first. Groovy is the default default.
2023-04-27 13:52:29 -04:00
Adam Treat
5a7d40f604
Move the saving of the tokens to the impl and not the callbacks responsibility.
2023-04-27 11:16:51 -04:00
Adam Treat
ba4b28fcd5
Move the promptCallback to own function.
2023-04-27 11:08:15 -04:00
Adam Treat
386ce08fca
Track check for updates.
2023-04-27 07:41:23 -04:00
Adam Treat
ee5c58c26c
Initial support for opt-in telemetry.
2023-04-26 22:05:56 -04:00
Adam Treat
a3d97fa009
Don't crash when prompt is too large.
2023-04-26 19:08:37 -04:00
Aaron Miller
15a979b327
new settings (model path, repeat penalty) w/ tabs
2023-04-25 16:24:55 -04:00
Adam Treat
cf8a4dd868
Infinite context window through trimming.
2023-04-25 11:20:51 -04:00
Adam Treat
a79bc4233c
Implement repeat penalty for both llama and gptj in gui.
2023-04-25 08:38:29 -04:00
Adam Treat
a02b0c14ca
Don't crash right out of the installer ;)
2023-04-24 21:07:16 -04:00
Aaron Miller
29e3e04fcf
persistent threadcount setting
...
threadcount is now on the Settings object and
gets reapplied after a model switch
2023-04-24 18:05:08 -04:00
Adam Treat
74621109c9
Add a fixme for dubious code.
2023-04-24 14:03:04 -04:00
Adam Treat
c086a45173
Provide a non-priviledged place for model downloads when exe is installed to root.
2023-04-23 11:28:17 -04:00
Adam Treat
43e6d05d21
Don't crash starting with no model.
2023-04-20 07:17:07 -04:00
Adam Treat
55084333a9
Add llama.cpp support for loading llama based models in the gui. We now
...
support loading both gptj derived models and llama derived models.
2023-04-20 06:19:09 -04:00
Aaron Miller
f1b87d0b56
Add thread count setting
2023-04-19 08:33:13 -04:00
Adam Treat
e6cb6a2ae3
Add a new model download feature.
2023-04-18 21:10:06 -04:00
Adam Treat
1eda8f030e
Allow unloading/loading/changing of models.
2023-04-18 11:42:38 -04:00
Adam Treat
15ae0a4441
Fix the context.
2023-04-17 14:11:41 -04:00
Adam Treat
659ab13665
Don't allow empty prompts. Context past always equal or greater than zero.
2023-04-16 14:57:58 -04:00
Adam Treat
7e9ca06366
Trim trailing whitespace at the end of generation.
2023-04-16 14:19:59 -04:00
Adam Treat
fdf7f20d90
Remove newlines too.
2023-04-16 14:04:25 -04:00
Adam Treat
f8b962d50a
More conservative default params and trim leading whitespace from response.
2023-04-16 13:56:56 -04:00
Aaron Miller
cb6d2128d3
use the settings dialog settings when generating
2023-04-16 11:16:30 -04:00
Adam Treat
2354779ac1
Provide an instruct/chat template.
2023-04-15 16:33:37 -04:00
Aaron Miller
0f9b80e6b6
Use completeBaseName to display model name
...
this cuts the filename at the *final* dot instead of the first, allowing
model names with version numbers to be displayed correctly.
2023-04-15 13:29:51 -04:00
Adam Treat
2f3a46c17f
Erase the correct amount of logits when regenerating which is not the same
...
as the number of tokens.
2023-04-15 09:19:54 -04:00
Adam Treat
12bf78bf24
Fix crash with recent change to erase context.
2023-04-15 09:10:34 -04:00
Adam Treat
f8005cff45
When regenerating erase the previous response and prompt from the context.
2023-04-15 09:10:27 -04:00
Adam Treat
9de185488c
Add an abstraction around gpt-j that will allow other arch models to be loaded in ui.
2023-04-13 22:15:40 -04:00
Adam Treat
0d8b5bbd49
Fix the check for updates on mac.
2023-04-12 17:57:02 -04:00
Adam Treat
c183702aa4
Provide a busy indicator if we're processing a long prompt and make the
...
stop button work in the middle of processing a long prompt as well.
2023-04-12 15:31:32 -04:00
Adam Treat
72b964e064
Fix the name of the updates tool.
2023-04-11 12:16:04 -04:00
Adam Treat
0ea31487e3
Programmatically get the model name from the LLM. The LLM now searches
...
for applicable models in the directory of the executable given a pattern
match and then loads the first one it finds.
Also, add a busy indicator for model loading.
2023-04-11 08:29:55 -04:00
Adam Treat
a56a258099
Big updates to the UI.
2023-04-10 23:34:34 -04:00
Adam Treat
b1b7744241
Add a reset context feature to clear the chat history and the context for now.
2023-04-10 17:13:22 -04:00
Adam Treat
ae91bfa48a
Fixes for linux and macosx.
2023-04-10 16:33:14 -04:00
