Archives/gpt4all
2
0
Fork 0
mirror of https://github.com/nomic-ai/gpt4all synced 2024-11-10 01:10:35 +00:00
Code Issues Packages Projects Releases Wiki Activity
2,027 Commits 543 Branches 59 Tags 51 MiB
be91576937
Commit Graph

2027 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Jared Van Bortel
4193533154
models.json: add Phi-3 Mini Instruct (#2252) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-23 18:53:09 -04:00
Ikko Eltociear Ashimine
baf1dfc5d7
docs: update README.md (#2250) 
minor fix

Signed-off-by: Ikko Eltociear Ashimine <eltociear@gmail.com>
 2024-04-23 13:26:47 -04:00
Jared Van Bortel
0b78b79b1c
models.json: add Llama 3 Instruct 8B (#2242) 
Other changes:
* fix 'requires' for models with %2 in template
* move Ghost 7B to the appropriate location in the file based on where it actually appears in the UI

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-19 13:09:44 -04:00
Jared Van Bortel
aac00d019a
chat: temporarily revert some UI changes before next release (#2234) 
* chat: revert PR #2187

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

* chat: revert PR #2148

This reverts commit f571e7e450.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

---------

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-18 14:52:29 -04:00
Jared Van Bortel
ba53ab5da0
python: do not print GPU name with verbose=False, expose this info via properties (#2222) 
* llamamodel: only print device used in verbose mode

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

* python: expose backend and device via GPT4All properties

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

* backend: const correctness fixes

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

* python: bump version

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

* python: typing fixups

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

* python: fix segfault with closed GPT4All

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

---------

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-18 14:52:02 -04:00
Jared Van Bortel
271d752701
localdocs: small but important fixes to local docs (#2236) 
* chat: use .rmodel extension for Nomic Embed

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

* database: fix order of SQL arguments in updateDocument

Signed-off-by: Jared Van Bortel <jared@nomic.ai>

---------

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-18 14:51:13 -04:00
Jared Van Bortel
be93ee75de
responsetext : fix markdown code block trimming (#2232) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-18 14:50:32 -04:00
Andriy Mulyar
4ebb0c6ac0
Remove town hall announcement from readme (#2237) 
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
 2024-04-18 12:54:50 -04:00
Andriy Mulyar
2c4c101b2e
Roadmap update (#2230) 
* Roadmap update

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

* Spelling error

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

* Update README.md

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

* Update README.md

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

---------

Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
 2024-04-17 12:19:57 -04:00
Jared Van Bortel
38cc778a0c
models.json: use simpler system prompt for Mistral OpenOrca (#2220) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-15 18:02:51 -04:00
Adam Treat
94a9943782 Change the behavior of show references setting for localdocs. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-04-15 14:30:26 -05:00
Adam Treat
e27653219b Fix bugs with the context link text for localdocs to make the context links 
persistently work across application loads and fix scrolling bug with context
links.

Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-04-15 14:30:26 -05:00
Jared Van Bortel
ac498f79ac
fix regressions in system prompt handling (#2219) 
* python: fix system prompt being ignored
* fix unintended whitespace after system prompt

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-15 11:39:48 -04:00
dependabot[bot]
2273cf145e build(deps): bump tar in /gpt4all-bindings/typescript 
Bumps [tar](https://github.com/isaacs/node-tar) from 6.2.0 to 6.2.1.
- [Release notes](https://github.com/isaacs/node-tar/releases)
- [Changelog](https://github.com/isaacs/node-tar/blob/main/CHANGELOG.md)
- [Commits](https://github.com/isaacs/node-tar/compare/v6.2.0...v6.2.1)

---
updated-dependencies:
- dependency-name: tar
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
 2024-04-15 08:37:39 -05:00
Jared Van Bortel
3f8257c563
llamamodel: fix semantic typo in nomic client dynamic mode (#2216) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-12 17:25:15 -04:00
Jared Van Bortel
46818e466e
python: embedding cancel callback for nomic client dynamic mode (#2214) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-12 16:00:39 -04:00
Jared Van Bortel
459289b94c
embed4all: small fixes related to nomic client local embeddings (#2213) 
* actually submit larger batches with increased n_ctx
* fix crash when llama_tokenize returns no tokens

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-12 10:54:15 -04:00
Andriy Mulyar
1e4c62027b
Update README.md (#2209) 
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
 2024-04-10 16:27:46 -04:00
Jared Van Bortel
1b84a48c47
python: add list_gpus to the GPT4All API (#2194) 
Other changes:
* fix memory leak in llmodel_available_gpu_devices
* drop model argument from llmodel_available_gpu_devices
* breaking: make GPT4All/Embed4All arguments past model_name keyword-only

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-04-04 14:52:13 -04:00
Adam Treat
790320e170 Use consistent names for LocalDocs 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-04-03 08:02:52 -05:00
Adam Treat
aad502f336 Rename these to views. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-04-03 08:02:52 -05:00
Adam Treat
77d5adfb02 Changes to the UI and icons. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-04-03 08:02:52 -05:00
3Simplex
9c23d44ad3 Update ChatView.qml 
Directed the Documentation link specifically to the ChatUI documentation.


Co-authored-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>

Signed-off-by: 3Simplex <10260755+3Simplex@users.noreply.github.com>
 2024-04-01 08:34:49 -05:00
3Simplex
4f6c43aec9 Update ChatView.qml 
Include links for Documentation and FAQ for new users on the "new chat view".


Co-authored-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>

Signed-off-by: 3Simplex <10260755+3Simplex@users.noreply.github.com>
 2024-04-01 08:34:49 -05:00
Robin Verduijn
4852d39699 Fix to set proper app icon on MacOS. 
Signed-off-by: Robin Verduijn <robinverduijn.github@gmail.com>
 2024-04-01 08:34:02 -05:00
Jared Van Bortel
3313c7de0d
python: implement close() and context manager interface (#2177) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-28 16:48:07 -04:00
dependabot[bot]
dddaf49428
typescript: bump ip dep from 2.0.0 to 2.0.1 (#2175) 
Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-28 12:58:03 -04:00
Jacob Nguyen
55f3b056b7
typescript!: chatSessions, fixes, tokenStreams (#2045) 
Signed-off-by: jacob <jacoobes@sern.dev>
Signed-off-by: limez <limez@protonmail.com>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Co-authored-by: limez <limez@protonmail.com>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-28 12:08:23 -04:00
Jared Van Bortel
6c8a44f6c4
ci: use aws s3 sync to upload docs (#2172) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-27 11:03:10 -04:00
Jared Van Bortel
b743c588e8
python: bump version to 2.3.2 to include *all* of the bugfixes (#2171) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-26 15:26:08 -04:00
Jared Van Bortel
67843edc7c
backend: update llama.cpp submodule for wpm locale fix (#2163) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-26 11:04:22 -04:00
Jared Van Bortel
83ada4ca89
backend: update llama.cpp submodule for Unicode paths fix (#2162) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-26 11:01:02 -04:00
Jared Van Bortel
8d09b2c264 python: bump version 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-25 22:16:50 -07:00
Jared Van Bortel
446668674e python: use TypedDict from typing_extensions on python 3.9 and 3.10 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-25 22:16:50 -07:00
Jared Van Bortel
adea3811ea docs: fix mention of Q6_K quantization in README 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-25 11:03:18 -05:00
Jared Van Bortel
71db8bdc80
python: also delete partial file on KeyboardInterrupt/SystemExit (#2154) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-21 12:59:35 -04:00
Jared Van Bortel
71d7f34d1a
python: improve handling of incomplete downloads (#2152) 
* make sure encoding is identity for Range requests
* use a .part file for partial downloads
* verify using file size and MD5 from models3.json

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-21 11:33:41 -04:00
Adam Treat
b4bcc5b37c Fix colors for server chat in all themes. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-20 15:10:26 -05:00
Adam Treat
f571e7e450 Preliminary redesign of the UI. This has no major regression. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-20 11:45:26 -05:00
Jared Van Bortel
0455b80b7f
Embed4All: optionally count tokens, misc fixes (#2145) 
Key changes:
* python: optionally return token count in Embed4All.embed
* python and docs: models2.json -> models3.json
* Embed4All: require explicit prefix for unknown models
* llamamodel: fix shouldAddBOS for Bert and Nomic Bert

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-20 11:24:02 -04:00
Lam Hieu
271e6a529c Rename the model for more clarity 
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
 2024-03-20 10:16:25 -05:00
Lam Hieu
5732928b93 Change download url 
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
 2024-03-20 10:16:25 -05:00
Lam Hieu
6a22b81f44 Update Ghost 7B v0.9.1 configuration 
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
 2024-03-20 10:16:25 -05:00
Lam Hieu
f50bf856b3 Fix invalid model configuration 
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
 2024-03-20 10:16:25 -05:00
Lam Hieu
df79e45195 Support Ghost 7B v0.9.1, fast, powerful and smooth for Vietnamese and English languages. 
Signed-off-by: Lam Hieu <lamhieu.vk@gmail.com>
 2024-03-20 10:16:25 -05:00
Jacob Nguyen
0e9e5237c5
ci: fix build-ts-docs with npm install --ignore-scripts (#2143) 
Signed-off-by: Jacob Nguyen <76754747+jacoobes@users.noreply.github.com>
 2024-03-19 17:28:14 -04:00
Jared Van Bortel
a1bb6084ed
python: documentation update and typing improvements (#2129) 
Key changes:
* revert "python: tweak constructor docstrings"
* docs: update python GPT4All and Embed4All documentation
* breaking: require keyword args to GPT4All.generate

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-19 17:25:22 -04:00
Jared Van Bortel
f30151491d Revert "ci: fix failing build-ts-docs workflow (#2142)" 
According to jacoobes, --ignore-scripts was removed in yarn v2.

This reverts commit c6bd8577a9.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-19 12:28:43 -04:00
Jacob Nguyen
c6bd8577a9
ci: fix failing build-ts-docs workflow (#2142) 
Signed-off-by: Jacob Nguyen <76754747+jacoobes@users.noreply.github.com>
 2024-03-19 12:20:53 -04:00
Jared Van Bortel
699410014a
fix non-AVX CPU detection (#2141) 
* chat: fix non-AVX CPU detection on Windows
* bindings: throw exception instead of logging to console

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-19 10:56:14 -04:00