AI/gpt4all
1
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all.git synced 2024-10-01 01:06:10 -04:00
Code Issues Packages Projects Releases Wiki Activity
965 Commits 491 Branches 56 Tags 46 MiB
d3ba1295a7
Commit Graph

965 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Aaron Miller
d3ba1295a7
Metal+LLama take two (#929) 
Support latest llama with Metal
---------

Co-authored-by: Adam Treat <adam@nomic.ai>
Co-authored-by: niansa/tuxifan <tuxifan@posteo.de>
 2023-06-09 16:48:46 -04:00
Adam Treat
b162b5c64e Revert "llama on Metal (#885)" 
This reverts commit c55f81b860.
 2023-06-09 15:08:46 -04:00
Aaron Miller
c55f81b860
llama on Metal (#885) 
Support latest llama with Metal

---------

Co-authored-by: Adam Treat <adam@nomic.ai>
Co-authored-by: niansa/tuxifan <tuxifan@posteo.de>
 2023-06-09 14:58:12 -04:00
niansa/tuxifan
14e9ccbc6a Do auto detection by default in C++ API 
Signed-off-by: niansa/tuxifan <tuxifan@posteo.de>
 2023-06-09 17:01:19 +02:00
Richard Guo
e0a8480c0e
Generator in Python Bindings - streaming yields tokens at a time (#895) 
* generator method

* cleanup

* bump version number for clarity

* added replace in decode to avoid unicodedecode exception

* revert back to _build_prompt
 2023-06-09 10:17:44 -04:00
niansa/tuxifan
f03da8d732 Removed double-static from variables in replit.cpp 
The anonymous namespace already makes it static.

Signed-off-by: niansa/tuxifan <tuxifan@posteo.de>
 2023-06-09 08:55:15 -04:00
pingpongching
0d0fae0ca8 Change the default values for generation in GUI 2023-06-09 08:51:09 -04:00
Adam Treat
8fb73c2114 Forgot to bump. 2023-06-09 08:45:31 -04:00
Richard Guo
be2310322f update models json with replit model 2023-06-09 08:44:46 -04:00
Adam Treat
f2387d6f77 Always sync for circleci. 2023-06-09 08:42:49 -04:00
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