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
1,363 Commits 491 Branches 56 Tags 46 MiB
85e34598f9
Commit Graph

1363 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Adam Treat
85e34598f9 more circleci 2023-08-31 15:29:54 -04:00
Adam Treat
9f1cbad4f1 more Circleci 2023-08-31 15:29:54 -04:00
Adam Treat
202805637b More circleci 2023-08-31 15:29:54 -04:00
Adam Treat
2832fad965 More circleci 2023-08-31 15:29:54 -04:00
Adam Treat
6a309e2ac8 More circleci 2023-08-31 15:29:54 -04:00
Adam Treat
94969a4199 More circleci 2023-08-31 15:29:54 -04:00
Adam Treat
1a2a9791bd More circleci 2023-08-31 15:29:54 -04:00
Adam Treat
8d80f7963e More circleci 2023-08-31 15:29:54 -04:00
Adam Treat
1723f82aaa More circleci 2023-08-31 15:29:54 -04:00
Adam Treat
3bdc87ff4a More circleci 2023-08-31 15:29:54 -04:00
Adam Treat
5e5a235639 More circleci 2023-08-31 15:29:54 -04:00
Adam Treat
4521c71b4e More circleci 2023-08-31 15:29:54 -04:00
Adam Treat
2f1c995739 More circleci 2023-08-31 15:29:54 -04:00
Adam Treat
84e08858a8 Fix missing run in circleci 2023-08-31 15:29:54 -04:00
Adam Treat
6fd6369ab3 Fix yaml parsing 2023-08-31 15:29:54 -04:00
Adam Treat
54bc61e280 Make it work on gpt4all-backend linux circleci too. 2023-08-31 15:29:54 -04:00
Adam Treat
320eda9685 Get VulkanSDK installed on linux circleci. 2023-08-31 15:29:54 -04:00
Adam Treat
f578fa6cdf Fix for windows. 2023-08-31 15:29:54 -04:00
Adam Treat
17d3e4976c Add a comment indicating future work. 2023-08-31 15:29:54 -04:00
Adam Treat
7ec522dfb0 Lower case the som. 2023-08-31 15:29:54 -04:00
Adam Treat
7ae6bfc928 Add SOM to codespell ignore list. 2023-08-31 15:29:54 -04:00
Adam Treat
987546c63b Nomic vulkan backend licensed under the Software for Open Models License (SOM), version 1.0. 2023-08-31 15:29:54 -04:00
Adam Treat
d55cbbee32 Update to newer llama.cpp and disable older forks. 2023-08-31 15:29:54 -04:00
Aaron Miller
0bc2274869 bump llama.cpp version + needed fixes for that 2023-08-31 15:29:54 -04:00
aaron miller
33c22be2aa starcoder: use ggml_graph_plan 2023-08-31 15:29:54 -04:00
Bob van Luijt
27a8b020c3
Add Weaviate integration (#1368) 
* Add Weaviate integration

Signed-off-by: Bob van Luijt <bob@weaviate.io>

* Created integrations section

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

---------

Signed-off-by: Bob van Luijt <bob@weaviate.io>
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
Co-authored-by: Andriy Mulyar <andriy.mulyar@gmail.com>
 2023-08-23 16:53:30 -04:00
Andriy Mulyar
36f7fb5848
Update README.md with download statistics 
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
 2023-08-17 16:56:28 -04:00
Jacob Nguyen
b43eec0e2c
fix ts tests on windows (#1342) 
* fix ts tests on windows

* fix cleanup

* fix tests

* hold on c sharp workflows

* fix: downloadModel doesnt not mkdirp
 2023-08-17 10:32:08 -04:00
Adam Treat
a63093554f Remove older models that rely upon soon to be no longer supported quantization formats. 2023-08-15 13:19:41 -04:00
Andriy Mulyar
a9668eb2e4 Added optional top_p and top_k 2023-08-15 12:06:49 -04:00
Adam Treat
2c0ee50dce Add starcoder 7b. 2023-08-15 09:27:55 -04:00
Jacob Nguyen
4e55940edf
feat(typescript)/dynamic template (#1287) (#1326) 
* feat(typescript)/dynamic template (#1287)

* remove packaged yarn

* prompt templates update wip

* prompt template update

* system prompt template, update types, remove embed promises, cleanup

* support both snakecased and camelcased prompt context

* fix #1277 libbert, libfalcon and libreplit libs not being moved into the right folder after build

* added support for modelConfigFile param, allowing the user to specify a local file instead of downloading the remote models.json. added a warning message if code fails to load a model config. included prompt context docs by amogus.

* snakecase warning, put logic for loading local models.json into listModels, added constant for the default remote model list url, test improvements, simpler hasOwnProperty call

* add DEFAULT_PROMPT_CONTEXT, export new constants

* add md5sum testcase and fix constants export

* update types

* throw if attempting to list models without a source

* rebuild docs

* fix download logging undefined url, toFixed typo, pass config filesize in for future progress report

* added overload with union types

* bump to 2.2.0, remove alpha

* code speling

---------

Co-authored-by: Andreas Obersteiner <8959303+iimez@users.noreply.github.com>
 2023-08-14 12:45:45 -04:00
Elin Angelov
4d855afe97
Update README.md (#1260) 
* Update README.md

Signed-off-by: Elin Angelov <me@zetxx.eu>

* Update README.md

Signed-off-by: Elin Angelov <me@zetxx.eu>

* Update README.md

Signed-off-by: Elin Angelov <me@zetxx.eu>

* Changed wording a tiny bit again

Signed-off-by: niansa/tuxifan <tuxifan@posteo.de>

* Added missing space

Signed-off-by: niansa/tuxifan <tuxifan@posteo.de>

---------

Signed-off-by: Elin Angelov <me@zetxx.eu>
Signed-off-by: niansa/tuxifan <tuxifan@posteo.de>
Co-authored-by: niansa/tuxifan <tuxifan@posteo.de>
 2023-08-11 14:14:53 -04:00
cosmic-snow
af6fe5fbb5 Update gpt4all_faq.md 
- minor oversight: there are now six supported architectures
- LLAMA -> LLaMA (for v1)
- note about Llama 2 and link to license
- limit some of the paragraphs to 150 chars


Signed-off-by: cosmic-snow <134004613+cosmic-snow@users.noreply.github.com>
 2023-08-10 23:56:54 +02:00
Victor Tsaran
ca8baa294b
Updated README.md with a wishlist idea (#1315) 
Signed-off-by: Victor Tsaran <vtsaran@yahoo.com>
 2023-08-10 11:27:09 -04:00
David Okpare
889c8d1758
Add embeddings endpoint for gpt4all-api (#1314) 
* Add embeddings endpoint

* Add test for embedding endpoint
 2023-08-10 10:43:07 -04:00
Cosmic Snow
108d950874 Fix Windows unable to load models on older Windows builds 
- Replace high-level IsProcessorFeaturePresent
- Reintroduce low-level compiler intrinsics implementation
 2023-08-09 09:27:43 +02:00
Lakshay Kansal
0f2bb506a8
font size changer and updates (#1322) 2023-08-07 13:54:13 -04:00
Akarshan Biswas
c449b71b56
Add LLaMA2 7B model to model.json. (#1296) 
* Add LLaMA2 7B model to model.json.

---------

Signed-off-by: Akarshan Biswas <akarshan.biswas@gmail.com>
 2023-08-02 16:58:14 +02:00
Lakshay Kansal
cbdcde8b75
scrollbar fixed for main chat and chat drawer (#1301) 2023-07-31 12:18:38 -04:00
Lakshay Kansal
3d2db76070
fixed issue of text color changing for code blocks in light mode (#1299) 2023-07-31 12:18:19 -04:00
Cosmic Snow
55f96aacc6 Move FAQ entries to general FAQ and adjust, plus minor improvements 2023-07-31 01:34:06 +02:00
Cosmic Snow
e56f977b67 Move Chat GUI out of the Bindings group in the docs navigation. 2023-07-31 01:34:06 +02:00
Cosmic Snow
e285ce91da black & isort 
Please enter the commit message for your changes. Lines starting
 2023-07-31 01:34:06 +02:00
Cosmic Snow
19d6460282 Extend & Update Python documentation 
- Expand Quickstart
  - Add Examples & Explanations:
    - Info on generation parameters
    - Model folder examples
    - Templates
    - Introspection with logging
    - Notes on allow_download=False
    - Interrupting generation (response callback)
    - FAQ
 2023-07-31 01:34:06 +02:00
Cosmic Snow
83ad6b42c4 Add build hint to Python Readme 
- CMake build can be told run in Release mode
 2023-07-31 01:34:06 +02:00
385olt
3ed6d176a5
Python bindings: unicode decoding (#1281) 
* rewrote the unicode decoding using the structure of multi-byte unicode symbols.
 2023-07-30 11:29:51 -07:00
Zach Nussbaum
91a32c0e84
ci: pin (#1292) 2023-07-28 17:00:56 -04:00
Andriy Mulyar
39acbc8378
Python version bump 
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
 2023-07-27 12:19:23 -04:00
Aaron Miller
b9e2553995
remove trailing comma from models json (#1284) 2023-07-27 09:14:33 -07:00