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
2,012 Commits 491 Branches 56 Tags 46 MiB
8fd9f01578
Commit Graph

2012 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Jared Van Bortel
8fd9f01578 replace setShouldBeLoaded with loadModelAsync/releaseModelAsync 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-08-09 11:31:03 -04:00
Jared Van Bortel
05bd6042b6 cleanup function braces 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-08-08 16:10:28 -04:00
Jared Van Bortel
39f5c53638 create a generic interface for LlamaCppModel, called LLModel 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-08-08 15:54:24 -04:00
Jared Van Bortel
f2e5c931fe rename ChatLLM to LlamaCppModel 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-08-08 15:14:58 -04:00
Jared Van Bortel
429613ac32 fix some #includes with IWYU 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-08-07 18:00:49 -04:00
Jared Van Bortel
5be5314ace rename LLModel -> ModelBackend, EmbLLModel -> EmbCapableBackend 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-08-07 17:53:58 -04:00
Jared Van Bortel
bafbed9c6b rename LlamaCppBackend::Implementation to LlamaCppBackendManager 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-08-07 17:53:52 -04:00
Jared Van Bortel
f1f60d6ef8 chatllm: clean up API 
Some functions did not need to be public or did not need to exist at
all.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-08-07 16:37:24 -04:00
Jared Van Bortel
595501fcde backend: move more stuff into LlamaCppBackend 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-08-07 11:33:50 -04:00
Jared Van Bortel
9808be5e73 rename LLamaModel to LlamaCppBackendImpl 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-08-07 11:33:50 -04:00
Jared Van Bortel
43b6f63589 remove unused llmodel_shared.h 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-08-07 11:33:50 -04:00
Jared Van Bortel
de7cb36fcc
python: reduce size of wheels built by CI, other build tweaks (#2802) 
* Read CMAKE_CUDA_ARCHITECTURES directly
* Disable CUBINs for python build in CI
* Search for CUDA 11 as well as CUDA 12

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-08-07 11:27:50 -04:00
Jared Van Bortel
be66ec8ab5
chat: faster KV shift, continue generating, fix stop sequences (#2781) 
* Don't stop generating at end of context
* Use llama_kv_cache ops to shift context
* Fix and improve reverse prompt detection
* Replace prompt recalc callback with a flag to disallow context shift
 2024-08-07 11:25:24 -04:00
Jared Van Bortel
90de2d32f8
chat: add CHANGELOG.md (#2699) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-08-07 11:20:15 -04:00
Jared Van Bortel
80fd02bdbc
ci: explicitly build with 4 jobs on Linux (#2799) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-08-05 17:53:23 -04:00
Jared Van Bortel
1f2294ed73
python: prepare to release v2.8.0 (#2794) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-08-05 13:36:18 -04:00
Jared Van Bortel
10c3e21147
python: detect Rosetta 2 (#2793) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-08-05 13:24:06 -04:00
Riccardo Giovanetti
01f51cfa1b
translations: update Italian translation (#2786) 
Signed-off-by: Riccardo Giovanetti <riccardo.giovanetti@gmail.com>
 2024-08-05 10:49:52 -04:00
cosmic-snow
828d83094b
docs: replace default model & link to wiki in CLI readme (#2719) 
Signed-off-by: cosmic-snow <134004613+cosmic-snow@users.noreply.github.com>
 2024-08-04 19:44:01 -04:00
Jared Van Bortel
51bd01ae05
backend: fix extra spaces in tokenization and a CUDA crash (#2778) 
Also potentially improves accuracy of BOS insertion, token cache, and logit indexing.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-08-01 10:46:36 -04:00
Riccardo Giovanetti
da59c9f5ea
Updated Italian localization file (#2783) 
Signed-off-by: Riccardo Giovanetti <riccardo.giovanetti@gmail.com>
 2024-08-01 09:19:18 -04:00
Jared Van Bortel
6b8e0f7ae4
chat: fix comparison of versions with suffixes (#2772) 
Pre-release and post-release suffixes are now interpreted correctly. Also fix comparison of incomplete versions.

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-07-30 13:20:52 -04:00
ThiloteE
e45685b27a
Models: Add Qwen2-1.5B-Instruct (#2759) 
Signed-off-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
 2024-07-29 09:57:33 -04:00
AT
78cc324e8c
Don't compare non-numeric parts of the version string. (#2762) 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-07-28 11:36:16 -04:00
cosmic-snow
ee6064b608
Fix LocalDocs file icons in sources display (mixed case) (#2761) 
Minor, cosmetic fix to the file icon which is shown as a LocalDocs source.
A recent commit has allowed the file suffixes to be mixed case, this makes the
displayed icon consistent, so that e.g. '.PDF' is uses the right icon, as well.

Signed-off-by: Cosmic Snow <cosmic-snow@mailfence.com>
 2024-07-28 10:06:30 -04:00
Adam Treat
f3734e5de8 Fix download url for llama3.1 128k. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-07-27 17:18:06 -04:00
Adam Treat
fb853c7f30 Replace llama 3.1 with corrected version. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-07-27 17:07:35 -04:00
Adam Treat
52e076e9a1 Add release notes for v3.1.1 and bump version 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-07-27 17:01:54 -04:00
Adam Treat
4bbd0360a0 Bump version to v3.1.1 for llama 3.1 fix 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-07-27 14:17:29 -04:00
AT
8c834a5177
Update llama.cpp to include upstream Llama 3.1 RoPE fix. (#2758) 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-07-27 14:14:19 -04:00
wuhanodoo
257bedb48e
Update gpt4all_zh_CN.ts some not translated (#2749) 
Signed-off-by: wuhanodoo <99947164+wuodoo@users.noreply.github.com>
 2024-07-26 13:21:46 -04:00
patcher9
71c957f8ee
Update monitoring.md (#2724) 
Signed-off-by: patcher9 <patcher99@dokulabs.com>
 2024-07-25 19:13:00 -04:00
Tim453
7fefac74ba
Update Flatpak appdata (#2727) 
- Added maintainer for the flatpak
- Update screenshots
- Remove the mentioning of gpt-j model support
- Removed the flatpak manifest, the current version is here https://github.com/flathub/io.gpt4all.gpt4all

Signed-off-by: Tim <tim453@mailbox.org>
Signed-off-by: AT <manyoso@users.noreply.github.com>
Co-authored-by: AT <manyoso@users.noreply.github.com>
 2024-07-25 16:05:17 -04:00
AT
241969f299
Update translations for strings in latest main. (#2735) 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-07-25 15:47:20 -04:00
不知火 Shiranui
f9cd2e321c
feat: add openai-compatible api models (#2683) 
Signed-off-by: Shiranui <supersonic@livemail.tw>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
 2024-07-25 10:02:52 -04:00
ThiloteE
6b97d0f8ea
Update README.md of gpt4all-chat (#2698) 
- updates features
- removes feature wish-list
- removes any mention of gpt-j since support for it has been removed

Signed-off-by: ThiloteE <73715071+ThiloteE@users.noreply.github.com>
 2024-07-25 09:20:31 -04:00
wuhanodoo
5623331a3c
Update gpt4all_zh_CN.ts, fix some not translated ,to merge (#2716) 
Signed-off-by: wuhanodoo <99947164+wuodoo@users.noreply.github.com>
 2024-07-25 09:19:17 -04:00
Thiago Ramos
6f15092f58
pt-BR translations (#2733) 
Signed-off-by: Thiago Ramos <thiagojramos@outlook.com>
 2024-07-25 09:18:44 -04:00
3Simplex
093c0332eb
Models json 310 Lowercase hash (#2732) 
Signed-off-by: 3Simplex <10260755+3Simplex@users.noreply.github.com>
 2024-07-24 17:05:13 -04:00
3Simplex
3dbc8da89e
updated models3.json (#2731) 
Signed-off-by: 3simplex <10260755+3Simplex@users.noreply.github.com>
 2024-07-24 16:32:46 -04:00
Adam Treat
1b51ef52fd Adjust the language of the latest news a bit. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-07-24 13:13:54 -04:00
Adam Treat
dbe953254a Update latest news. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-07-24 12:04:14 -04:00
AT
34a72d6f99
Bump version and release notes for v3.1.0 (#2726) 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-07-24 12:03:10 -04:00
Adam Treat
03d460c732 Change to release v3.1.0 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-07-24 09:19:13 -04:00
AT
0cdd07b23f
Actually set the chat name and suggested follow-up question prompts. (#2723) 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-07-23 21:51:36 -04:00
AT
765e055597
Change the timeout for circle ci and add a fixme. (#2722) 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-07-23 17:01:46 -04:00
abhisomala
df510ef869
added tutorial and images for it (#2717) 
* added tutorial and images for it

Signed-off-by: Max Cembalest <mbcembalest@gmail.com>

* updated images

Signed-off-by: abhisomala <68791501+abhisomala@users.noreply.github.com>
Signed-off-by: Max Cembalest <mbcembalest@gmail.com>

* Minor updates

Signed-off-by: abhisomala <68791501+abhisomala@users.noreply.github.com>
Signed-off-by: Max Cembalest <mbcembalest@gmail.com>

* fix link & indent note callouts

Signed-off-by: mcembalest <70534565+mcembalest@users.noreply.github.com>
Signed-off-by: Max Cembalest <mbcembalest@gmail.com>

* added obsidian tutorial to sidebar and fixed formatting of note boxes

Signed-off-by: Max Cembalest <mbcembalest@gmail.com>

---------

Signed-off-by: Max Cembalest <mbcembalest@gmail.com>
Signed-off-by: abhisomala <68791501+abhisomala@users.noreply.github.com>
Signed-off-by: mcembalest <70534565+mcembalest@users.noreply.github.com>
Co-authored-by: mcembalest <70534565+mcembalest@users.noreply.github.com>
Co-authored-by: Max Cembalest <mbcembalest@gmail.com>
 2024-07-22 15:31:43 -04:00
Jared Van Bortel
2a7fe95ff4
llamamodel: always print special tokens (#2701) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-07-22 13:32:17 -04:00
Jared Van Bortel
4ca1d0411f
llamamodel: add DeepSeek-V2 to whitelist (#2702) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-07-22 13:32:04 -04:00
cosmic-snow
54ed30937f
Show scrollbar in CollectionsDrawer as needed (#2691) 
Signed-off-by: Cosmic Snow <cosmic-snow@mailfence.com>
 2024-07-19 16:56:20 -04:00