Adam Treat
ae20274a1d
Fix compile
2023-06-01 10:58:31 -04:00
niansa/tuxifan
8aa707fdb4
Cleaned up implementation management ( #787 )
...
* Cleaned up implementation management
* Initialize LLModel::m_implementation to nullptr
* llmodel.h: Moved dlhandle fwd declare above LLModel class
2023-06-01 16:51:46 +02:00
niansa/tuxifan
c8794eac2a
Implemented logging mechanism ( #785 )
2023-06-01 16:50:42 +02:00
mudler
3da205fb2e
Style
2023-06-01 10:36:22 -04:00
mudler
ea3f91ed24
Adapt makefile
2023-06-01 10:36:22 -04:00
mudler
96d3cfd053
Debug
2023-06-01 10:36:22 -04:00
mudler
3a29055606
Makefile changes (WIP to test)
2023-06-01 10:36:22 -04:00
mudler
2a6b6fc1b5
Adapt code
2023-06-01 10:36:22 -04:00
Andriy Mulyar
ed0bade24d
Documentation improvements on LocalDocs ( #790 )
...
* Update gpt4all_chat.md
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
* typo
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
---------
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
2023-06-01 10:29:29 -04:00
Adam Treat
8be42683ac
Add fixme's and clean up a bit.
2023-06-01 07:57:10 -04:00
niansa
b68d359b4f
Dlopen better implementation management (Version 2)
2023-06-01 07:44:15 -04:00
niansa/tuxifan
991a0e4bd8
Advanced avxonly autodetection ( #744 )
...
* Advanced avxonly requirement detection
2023-05-31 21:26:18 -04:00
Adam Treat
252ed8fdc0
Make all the toolbuttons highlight on hover.
2023-05-31 21:07:14 -04:00
Adam Treat
077baa4d49
Fixup the plus new chat button.
2023-05-31 20:42:00 -04:00
Adam Treat
ced0379e54
Use the proper text color for sending messages.
2023-05-31 20:31:59 -04:00
Adam Treat
098599f967
Fix warning.
2023-05-31 20:09:05 -04:00
Adam Treat
dbac9a617d
Draw the indicator for combobox to ensure it looks the same on all platforms.
2023-05-31 19:55:16 -04:00
Adam Treat
7d78ed50aa
Add a custom busy indicator to further align look and feel across platforms.
2023-05-31 19:28:09 -04:00
AT
9c6c09cbd2
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
5dea13af51
Fix offset of prompt/response icons for smaller text.
2023-05-31 14:26:59 -04:00
Adam Treat
9896ea6c10
Make the comboboxes align in UI.
2023-05-30 21:11:04 -04:00
Adam Treat
1824723c01
Some color and theme enhancements to make the UI contrast a bit better.
2023-05-30 21:03:40 -04:00
Adam Treat
35290d6d1b
Fix wording of this accessible description.
2023-05-30 20:01:12 -04:00
Adam Treat
b51fbda817
Add a hover and pressed to the visual indication of MyButton.
2023-05-30 19:58:37 -04:00
Adam Treat
0185bfb8d6
Use the new MyButton for the regenerate response button.
2023-05-30 19:10:38 -04:00
Adam Treat
61cbae6617
Add a label to the model loading visual indicator.
2023-05-30 18:24:26 -04:00
Adam Treat
26afbde1ae
Get rid of blocking behavior for regenerate response.
2023-05-30 18:17:59 -04:00
FoivosC
0e82d87032
construct and return the correct reponse when the request is a chat completion
2023-05-30 16:34:23 -04:00
Andriy Mulyar
fae8d65582
Fixed formatting of localdocs docs ( #770 )
2023-05-30 16:19:48 -04:00
Adam Treat
98207deb9d
Fix remove model from model download for regular models.
2023-05-30 16:16:09 -04:00
Adam Treat
4a317eeb33
Revert "New tokenizer implementation for MPT and GPT-J"
...
This reverts commit ee3469ba6c
2023-05-30 12:59:00 -04:00
Adam Treat
06434f0042
Revert "buf_ref.into() can be const now"
...
This reverts commit 840e011b75
2023-05-30 12:58:53 -04:00
Adam Treat
92bc92d232
Revert "add tokenizer readme w/ instructions for convert script"
...
This reverts commit 9c15d1f83e
2023-05-30 12:58:18 -04:00
aaron miller
9c15d1f83e
add tokenizer readme w/ instructions for convert script
2023-05-30 12:05:57 -04:00
Aaron Miller
840e011b75
buf_ref.into() can be const now
2023-05-30 12:05:57 -04:00
Aaron Miller
ee3469ba6c
New tokenizer implementation for MPT and GPT-J
...
Improves output quality by making these tokenizers more closely
match the behavior of the huggingface `tokenizers` based BPE
tokenizers these models were trained with.
Featuring:
* Fixed unicode handling (via ICU)
* Fixed BPE token merge handling
* Complete added vocabulary handling
2023-05-30 12:05:57 -04:00
Andriy Mulyar
7e18f179e9
Improved localdocs documentation ( #762 )
...
* Improved localdocs documentation
* Improved localdocs documentation
* Improved localdocs documentation
* Improved localdocs documentation
2023-05-30 11:26:34 -04:00
Andriy Mulyar
3bb19b5e91
LocalDocs documentation initial ( #761 )
...
* LocalDocs documentation initial
2023-05-30 08:35:26 -04:00
mvenditto
522dfdbfe1
C# Bindings - Prompt formatting ( #712 )
...
* Added support for custom prompt formatting
* more docs added
* bump version
2023-05-28 19:57:00 -04:00
Chase McDougall
8189aece48
fix(training instructions): model repo name ( #728 )
...
Signed-off-by: Chase McDougall <chasemcdougall@hotmail.com>
2023-05-28 19:56:24 -04:00
Nandakumar
4161bfba33
Update README.md ( #738 )
...
* Update README.md
fix golang gpt4all import path
Signed-off-by: Nandakumar <nandagunasekaran@gmail.com>
* Update README.md
Signed-off-by: Nandakumar <nandagunasekaran@gmail.com>
---------
Signed-off-by: Nandakumar <nandagunasekaran@gmail.com>
2023-05-28 19:51:11 -04:00
Joseph Mearman
6ec2e26cd1
tiny typo ( #739 )
2023-05-28 19:50:45 -04:00
Richard Guo
9f62d4d05f
hotfix default verbose optioin
2023-05-26 12:49:32 -04:00
Konstantin Gukov
6ec3efa355
one funcion to append .bin suffix
2023-05-26 09:24:03 -04:00
Konstantin Gukov
52efd17165
Correct indentation of the multiline error message
2023-05-26 09:24:03 -04:00
Konstantin Gukov
39bdd74ddd
Add optional verbosity
2023-05-26 09:24:03 -04:00
Konstantin Gukov
136a5ac30d
Correct return type
2023-05-26 09:24:03 -04:00
Konstantin Gukov
e362e18431
Do not ignore explicitly passed 4 threads
2023-05-26 09:24:03 -04:00
Konstantin Gukov
a2e2a64899
Redundant else
2023-05-26 09:24:03 -04:00
Konstantin Gukov
8229bb5477
1. Cleanup the interrupted download
...
2. with-syntax
2023-05-26 09:24:03 -04:00
