Archives/gpt4all
2
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all synced 2024-11-06 09:20:33 +00:00
Code Issues Packages Projects Releases Wiki Activity
915 Commits 540 Branches 59 Tags 51 MiB
964e2ffc1b
Commit Graph

915 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Juuso Alasuutari
8d822f9898 llmodel: constify some casts in LLModelWrapper 2023-05-22 08:54:46 -04:00
Juuso Alasuutari
f2528e6f62 llmodel: constify LLModel::threadCount() 2023-05-22 08:54:46 -04:00
Andriy Mulyar
98b435628f Improved documentation landing page (#665) 
* Better doc landing page

* Typo

* Improved docs landing page
 2023-05-21 23:14:18 -04:00
Juuso Alasuutari
f0b942d323 llmodel: fix wrong and/or missing prompt callback type 
Fix occurrences of the prompt callback being incorrectly specified, or
the response callback's prototype being incorrectly used in its place.

Signed-off-by: Juuso Alasuutari <juuso.alasuutari@gmail.com>
 2023-05-21 16:02:11 -04:00
Adam Treat
9e13f813d5 Only default mlock on macOS where swap seems to be a problem. 2023-05-21 10:27:04 -04:00
Adam Treat
d5dd4e87de Always default mlock to true. 2023-05-20 21:16:15 -04:00
Magnus Bengtsson
7c6b8395b4 Fix #614, where relative paths to includes makes imports fail (#644) 2023-05-20 16:36:29 -04:00
Andriy Mulyar
94237e1940 Update build_and_run.md (#636) 
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
 2023-05-18 21:40:17 -04:00
Richard Guo
279156e116 GPT4All Updated Docs and FAQ (#632) 
* working on docs

* more doc organization

* faq

* some reformatting
 2023-05-18 16:07:57 -04:00
Richard Guo
6c939989d3 Paginate through all issues for close_issues workflow (#630) 
Signed-off-by: Richard Guo <richardg7890@gmail.com>
 2023-05-18 14:30:47 -04:00
Richard Guo
1900d9dd31 Update close_issues.yml (#629) 
Signed-off-by: Richard Guo <richardg7890@gmail.com>
 2023-05-18 13:17:31 -04:00
Richard Guo
23ad01f202 Issue Management (#628) 
* better issue templates, forcing issue template

* close issues workflow

* closeissues workflow change
 2023-05-18 13:11:45 -04:00
Richard Guo
5cbf4f28e8 comment out pip job 2023-05-18 12:02:11 -04:00
Richard Guo
c679d35eb1 fixed response formatting when streaming 2023-05-18 12:02:11 -04:00
Richard Guo
860193b9e8 updating pip version 2023-05-18 12:02:11 -04:00
Richard Guo
4b583dd759 deploying new version with streaming 2023-05-18 12:02:11 -04:00
Shukri
14f4a1c4ba Fix typo in README 2023-05-17 09:56:20 -04:00
aaron miller
08f3bd2a82 backend: fix buffer overrun in repeat penalty code 
Caught with AddressSanitizer running a basic prompt test against llmodel
standalone. This fix allows ASan builds to complete a simple prompt
without illegal accesses but there are still notably several leaks.
 2023-05-17 07:54:10 -04:00
kuvaus
4f2b7f7be4 Bugfix on llmodel_model_create function 
Fixes the bug where llmodel_model_create prints "Invalid model file" even though the model is loaded correctly. Credits and thanks to @serendipity for the fix.
 2023-05-17 07:49:32 -04:00
drbh
596120b44a adds a simple cli chat repl (#566) 
* adds a simple cli chat repl

* add n thread support and append assistant response
 2023-05-16 16:47:54 -04:00
Andriy Mulyar
e7446e7b65 Update README.md with Docs (#607) 
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
 2023-05-16 16:15:00 -04:00
Richard Guo
7c03bacc19 Improvements to documentation (#606) 2023-05-16 15:29:27 -04:00
Andriy Mulyar
d729a4435f Chat doc typo (#605) 
* Added modal labs example to documentation

* Added gpt4all chat

* Typo

* Andriy can't spell
 2023-05-16 14:33:34 -04:00
Andriy Mulyar
e74f523071 Chat doc fixes (#604) 
* Added modal labs example to documentation

* Added gpt4all chat

* Typo

---------

Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
 2023-05-16 14:23:37 -04:00
Andriy Mulyar
90e6cf937b Added better documentation to web server example in docs (#603) 
* Added modal labs example to documentation

* Added gpt4all chat
 2023-05-16 14:17:35 -04:00
Andriy Mulyar
980ecb6370 Update gpt4all_chat.md (#601) 
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
 2023-05-16 13:15:00 -04:00
Andriy Mulyar
d30b136611 Typo (#600) 
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
 2023-05-16 13:07:27 -04:00
Adam Treat
1142b09377 Fix for windows/mac installers. 2023-05-16 13:06:42 -04:00
Adam Treat
125961cd17 Remove davinci-003 option. 2023-05-16 13:06:42 -04:00
Adam Treat
23dbee15d1 Bump the version. 2023-05-16 13:06:42 -04:00
Andriy Mulyar
a094bb5e1a Update gpt4all_chat.md (#598) 
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
 2023-05-16 13:02:19 -04:00
Andriy Mulyar
86beffc1f1 Update gpt4all_chat.md (#597) 
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
 2023-05-16 12:58:05 -04:00
Andriy Mulyar
39318b6288 Chat Client Documentation (#596) 
* GPT4All Chat Client Documentation

* Updated documentation wording
 2023-05-16 12:46:31 -04:00
kuvaus
a0b98dc55d gpt4all-backend: Add llmodel create and destroy functions (#554) 
* Add llmodel create and destroy functions

* Fix capitalization

* Fix capitalization

* Fix capitalization

* Update CMakeLists.txt

---------

Co-authored-by: kuvaus <kuvaus@users.noreply.github.com>
 2023-05-16 11:36:46 -04:00
kuvaus
4f021ebcbb gpt4all-backend: Add MSVC support to backend (#595) 
* Add MSVC compatibility

* Add _MSC_VER macro

---------

Co-authored-by: kuvaus <kuvaus@users.noreply.github.com>
 2023-05-16 11:35:33 -04:00
Yaroslav Halchenko
15f7f1fc6c [DATALAD RUNCMD] run codespell throughout 
=== Do not change lines below ===
{
 "chain": [],
 "cmd": "codespell -w",
 "exit": 0,
 "extra_inputs": [],
 "inputs": [],
 "outputs": [],
 "pwd": "."
}
^^^ Do not change lines above ^^^
 2023-05-16 11:33:59 -04:00
Yaroslav Halchenko
59616c5eaa fix ambigous typo 2023-05-16 11:33:59 -04:00
Yaroslav Halchenko
2a2b61890d Add rudimentary codespell config 2023-05-16 11:33:59 -04:00
Yaroslav Halchenko
3dfaf1e946 Add github action to codespell main on push and PRs 2023-05-16 11:33:59 -04:00
Adam Treat
a7f24eb46e Use the default for max_tokens to avoid errors. 2023-05-16 10:31:55 -04:00
Adam Treat
53c5d761a5 Add ability to remove models. 2023-05-16 10:31:55 -04:00
Adam Treat
8cdee4b0cb Send the prompt template with conversations to the datalake. 2023-05-16 10:31:55 -04:00
Adam Treat
04d405b47f Generate the new prompt/response pair before model loading in server mode. 2023-05-16 10:31:55 -04:00
Adam Treat
62ccd95f3d Add save/restore to chatgpt chats and allow serialize/deseralize from disk. 2023-05-16 10:31:55 -04:00
Adam Treat
97e1813494 Add large network icon background for chatgpt and server modes. 2023-05-16 10:31:55 -04:00
Adam Treat
fc6ab1f776 Preliminary support for chatgpt models. 2023-05-16 10:31:55 -04:00
Adam Treat
22dc2bc5d2 Use compact json format. 2023-05-16 10:31:55 -04:00
Aaron Miller
9aaa355d41 backend: dedupe tokenizing code in mpt/gptj 2023-05-16 10:30:19 -04:00
Aaron Miller
fc2869f0b7 backend: dedupe tokenizing code in gptj/mpt 2023-05-16 10:30:19 -04:00
Aaron Miller
16b7bf01a8 backend: make initial buf_size const in model impls 
more unifying mpt and gptj code - this one's never written so also
changing the name to be clearer
 2023-05-16 10:30:19 -04:00