Commit Graph

955 Commits

Author SHA1 Message Date
Claudius Ellsel
3c1b59f5c6
Move usage in Python bindings readme to own section (#907)
Have own section for short usage example, as it is not specific to local build

Signed-off-by: Claudius Ellsel <claudius.ellsel@live.de>
2023-06-09 10:13:35 +02:00
niansa
0cb2b86730 Synced llama.cpp.cmake with upstream 2023-06-08 18:21:32 -04:00
Adam Treat
343a6a308f Circleci builds for Linux, Windows, and macOS for gpt4all-chat. 2023-06-08 18:02:44 -04:00
Aaron Miller
47fbc0e309
non-llama: explicitly greedy sampling for temp<=0 (#901)
copied directly from llama.cpp - without this temp=0.0 will just
scale all the logits to infinity and give bad output
2023-06-08 11:08:30 -07:00
Aaron Miller
b14953e136
sampling: remove incorrect offset for n_vocab (#900)
no effect, but avoids a *potential* bug later if we use
actualVocabSize - which is for when a model has a larger
embedding tensor/# of output logits than actually trained token
to allow room for adding extras in finetuning - presently all of our
models have had "placeholder" tokens in the vocab so this hasn't broken
anything, but if the sizes did differ we want the equivalent of
`logits[actualVocabSize:]` (the start point is unchanged), not
`logits[-actualVocabSize:]` (this.)
2023-06-08 11:08:10 -07:00
Andriy Mulyar
eb26293205
Update CollectionsDialog.qml (#856)
Phrasing for localdocs

Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
2023-06-08 13:44:17 -04:00
Claudius Ellsel
39a7c35d03
Update README.md (#906)
Add PyPI link and add clickable, more specific link to documentation

Signed-off-by: Claudius Ellsel <claudius.ellsel@live.de>
2023-06-08 13:43:31 -04:00
Adam Treat
010a04d96f Revert "Synced llama.cpp.cmake with upstream (#887)"
This reverts commit 89910c7ca8.
2023-06-08 07:23:41 -04:00
Adam Treat
7e304106cc Fix for windows. 2023-06-07 12:58:51 -04:00
niansa/tuxifan
89910c7ca8
Synced llama.cpp.cmake with upstream (#887) 2023-06-07 09:18:22 -07:00
Richard Guo
c4706d0c14
Replit Model (#713)
* porting over replit code model to gpt4all

* replaced memory with kv_self struct

* continuing debug

* welp it built but lot of sus things

* working model loading and somewhat working generate.. need to format response?

* revert back to semi working version

* finally got rid of weird formatting

* figured out problem is with python bindings - this is good to go for testing

* addressing PR feedback

* output refactor

* fixed prompt reponse collection

* cleanup

* addressing PR comments

* building replit backend with new ggmlver code

* chatllm replit and clean python files

* cleanup

* updated replit to match new llmodel api

* match llmodel api and change size_t to Token

* resolve PR comments

* replit model commit comment
2023-06-06 17:09:00 -04:00
Andriy Mulyar
ef35eb496f Supports downloading officially supported models not hosted on gpt4all R2 2023-06-06 16:21:02 -04:00
Andriy Mulyar
266f13aee9
Update gpt4all_faq.md (#861)
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
2023-06-05 15:41:30 -04:00
Ettore Di Giacinto
44dc1ade62
Set thread counts after loading model (#836) 2023-06-05 21:35:40 +02:00
Adam Treat
fdffad9efe New release notes 2023-06-05 14:55:59 -04:00
Adam Treat
f5bdf7c94c Bump the version. 2023-06-05 14:32:00 -04:00
Adam Treat
c5de9634c9 Fix llama models on linux and windows. 2023-06-05 14:31:15 -04:00
Andriy Mulyar
d8e821134e
Revert "Fix bug with resetting context with chatgpt model." (#859)
This reverts commit 031d7149a7.
2023-06-05 14:25:37 -04:00
Adam Treat
ecfeba2710 Revert "Speculative fix for windows llama models with installer."
This reverts commit c99e03e22e.
2023-06-05 14:25:01 -04:00
Adam Treat
c99e03e22e Speculative fix for windows llama models with installer. 2023-06-05 13:21:08 -04:00
Andriy Mulyar
01071efc9c
Documentation for model sideloading (#851)
* Documentation for model sideloading

Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>

* Update gpt4all_chat.md

Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>

---------

Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
2023-06-05 12:35:02 -04:00
AT
ec8618628c
Update README.md (#854)
Signed-off-by: AT <manyoso@users.noreply.github.com>
2023-06-05 12:25:51 -04:00
AT
da757734ea
Release notes for version 2.4.5 (#853) 2023-06-05 12:10:17 -04:00
Richard Guo
f5f9f28f74 updated pypi version 2023-06-05 12:02:25 -04:00
Adam Treat
8a9ad258f4 Fix symbol resolution on windows. 2023-06-05 11:19:02 -04:00
Adam Treat
969ff0ee6b Fix installers for windows and linux. 2023-06-05 10:50:16 -04:00
Adam Treat
1d4c8e7091 These need to be installed for them to be packaged and work for both mac and windows. 2023-06-05 09:57:00 -04:00
Adam Treat
3a9cc329b1 Fix compile on mac. 2023-06-05 09:31:57 -04:00
Adam Treat
25eec33bda Try and fix mac. 2023-06-05 09:30:50 -04:00
Adam Treat
91f20becef Need this so the linux installer packages it as a dependency. 2023-06-05 09:23:43 -04:00
Adam Treat
812b2f4b29 Make installers work with mac/windows for big backend change. 2023-06-05 09:23:17 -04:00
Andriy Mulyar
2e5b114364
Update models.json
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
2023-06-04 20:48:45 -04:00
Andriy Mulyar
0db6fd6867
Update models.json (#838)
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
2023-06-04 20:36:12 -04:00
AT
d5cf584f8d
Remove older models that are not as popular. (#837)
* Remove older models that are not as popular.

* Update models.json

Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>

---------

Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
Co-authored-by: Andriy Mulyar <andriy.mulyar@gmail.com>
2023-06-04 20:26:43 -04:00
Adam Treat
f73333c6a1 Update to latest llama.cpp 2023-06-04 19:57:34 -04:00
Adam Treat
301d2fdbea Fix up for newer models on reset context. This fixes the model from totally failing after a reset context. 2023-06-04 19:31:20 -04:00
Adam Treat
bdba2e8de6 Allow for download of models hosted on third party hosts. 2023-06-04 19:02:43 -04:00
Adam Treat
5073630759 Try again with the url. 2023-06-04 18:39:36 -04:00
Adam Treat
6ba37f47c1 Trying out a new feature to download directly from huggingface. 2023-06-04 18:34:04 -04:00
AT
be3c63ffcd
Update build_and_run.md (#834)
Signed-off-by: AT <manyoso@users.noreply.github.com>
2023-06-04 15:39:32 -04:00
AT
5f95aa9fc6
We no longer have an avx_only repository and better error handling for minimum hardware requirements. (#833) 2023-06-04 15:28:58 -04:00
Adam Treat
9f590db98d Better error handling when the model fails to load. 2023-06-04 14:55:05 -04:00
AT
bbe195ee02
Backend prompt dedup (#822)
* Deduplicated prompt() function code
2023-06-04 08:59:24 -04:00
Ikko Eltociear Ashimine
945297d837 Update README.md
huggingface -> Hugging Face

Signed-off-by: Ikko Eltociear Ashimine <eltociear@gmail.com>
2023-06-04 08:46:37 -04:00
Adam Treat
bc624f5389 Add a collection immediately and show a placeholder + busy indicator in localdocs settings. 2023-06-03 10:09:17 -04:00
Peter Gagarinov
23391d44e0 Only default mlock on macOS where swap seems to be a problem
Repeating the change that once was done in https://github.com/nomic-ai/gpt4all/pull/663 but then was overriden by 48275d0dcc

Signed-off-by: Peter Gagarinov <pgagarinov@users.noreply.github.com>
2023-06-03 07:51:18 -04:00
Adam Treat
55055ca983 Add the ability to change the directory via text field not just 'browse' button. 2023-06-02 22:52:55 -04:00
Adam Treat
25ee51e2ca Actually use the theme dark color for window background. 2023-06-02 20:19:50 -04:00
Adam Treat
d9ddd373d6 Prevent flashing of white on resize. 2023-06-02 20:16:11 -04:00
Adam Treat
8aba76ad05 Min constraints on about dialog. 2023-06-02 20:05:47 -04:00