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
2,043 Commits 491 Branches 56 Tags 46 MiB
432430811d
Commit Graph

2043 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
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
Tim453
6c2542e540 Allow changing the install path 
This commit allow changing the install path during CMake configure step using the CMAKE_INSTALL_PREFIX variable. If the variable is not set, it still defaults to {CMAKE_BINARY_DIR}/install.

Signed-off-by: Tim453 <50015765+Tim453@users.noreply.github.com>
 2024-03-18 11:57:56 -05:00
jbl
2bb86f35ee Update README.md 
Add Phorm AI Badge

Signed-off-by: jbl <141294048+bentleylong@users.noreply.github.com>
 2024-03-18 08:34:18 -05:00
Jared Van Bortel
255568fb9a
python: various fixes for GPT4All and Embed4All (#2130) 
Key changes:
* honor empty system prompt argument
* current_chat_session is now read-only and defaults to None
* deprecate fallback prompt template for unknown models
* fix mistakes from #2086

Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-15 11:49:58 -04:00
Jared Van Bortel
53f109f519
llamamodel: fix macOS build (#2125) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-14 12:06:07 -04:00
Adam Treat
667f29c2a1 Split the main.qml into two pieces to support multiple views in future. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-14 09:42:23 -05:00
Adam Treat
97de30edd1 Fix bug with removing old .txt chatgpt files in favor of .rmodel 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-13 17:37:18 -05:00
Olyxz16
2c0a660e6e
feat: Add support for Mistral API models (#2053) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Signed-off-by: Cédric Sazos <cedric.sazos@tutanota.com>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-13 18:23:57 -04:00
Jared Van Bortel
406e88b59a
implement local Nomic Embed via llama.cpp (#2086) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-13 18:09:24 -04:00
Adam Treat
171f4e488e Restrict the chat view text width to a reasonable maximum. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-13 17:01:19 -05:00
Adam Treat
6adaa672b4 Default to expanded state. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-13 14:23:04 -05:00
Adam Treat
b68ebb7c15 Rework the left chat panel to be persistently open. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-13 14:23:04 -05:00
Xu Zhen
0072860d24 Fix compatibility with Qt 6.4 
Signed-off-by: Xu Zhen <xuzhen@users.noreply.github.com>
 2024-03-12 07:42:22 -05:00
Adam Treat
ef9717dbe9 Use translation function for newly introduced strings. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-11 20:39:34 -04:00
Kryotek
afbb30a523 Add context menus to the prompt and the responses 
Signed-off-by: Kryotek <gcda@outlook.it>
 2024-03-11 19:36:18 -05:00
Adam Treat
11db71e0a7 Bump version and release notes for v2.7.3 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-11 14:44:14 -04:00
Adam Treat
5ed9aea410 Don't clear installed models. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-11 14:08:40 -04:00
Adam Treat
e2f64f89c9 When the current chat has no model use the first index. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-11 14:00:51 -04:00
Adam Treat
0daf37ab8a Fixes issue #2105 by using the original url for the download. This fix is 
valid because we expect the url to contain the actual filename at the end.
This also allows huggingface to track the download as happening.

Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-11 12:54:39 -05:00
Adam Treat
a6a3e0048a Don't erase the settings, but ignore them. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-11 12:52:23 -05:00
Adam Treat
f36a2874eb Clean up settings properly for removed models and also when user manually deletes. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-11 12:52:23 -05:00
AT
0cc5a80656 Update README.md 
Signed-off-by: AT <manyoso@users.noreply.github.com>
 2024-03-11 11:05:49 -05:00
johannesploetner
c951a5b1d3 Update gpt4all-api/gpt4all_api/app/api_v1/routes/chat.py 
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
Signed-off-by: johannesploetner <52075191+johannesploetner@users.noreply.github.com>
 2024-03-11 09:58:47 -05:00
Johannes Plötner
026ee4e46b Implement /v1/chat/completions endpoint for CPU mode 
Signed-off-by: Johannes Plötner <johannes.w.m.ploetner@gmail.com>
 2024-03-11 09:58:47 -05:00
chrisbarrera
61d6765361 #2024 Update ModelSettings.qml to default model/char settings combobox to the currently selected chat model 
Signed-off-by: chrisbarrera <34655880+chrisbarrera@users.noreply.github.com>
 2024-03-10 09:26:38 -05:00
Adam Treat
59f99b7f21 Minor fixes to server port feature. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-09 10:32:53 -05:00
Daniel Alencar
fe653d1489 feat: added api server port setting 2024-03-09 09:26:40 -06:00
Jared Van Bortel
5c248dbec9
models: new MPT model file without duplicated token_embd.weight (#2006) 
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
 2024-03-08 17:18:38 -05:00
Adam Treat
6ed3d01f17 Fix issue #2087 where cloned models were lost and listed in download dialog erroneously. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-08 15:55:16 -06:00
Adam Treat
6c3903a303 Fixes issue #2092. Don't include disabled from GUI models in application 
default model list.

Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-08 11:21:38 -06:00
Adam Treat
8ee68d1b6f Increase indent for readability. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-08 10:31:09 -06:00
Adam Treat
4251b7beaa Fix issue #2077 part 2. Only sort when actually necessary. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-08 10:31:09 -06:00
Adam Treat
fc169e739a Add trailing commas for things that need to be added in the future. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-08 09:44:20 -06:00
Adam Treat
028a8db6ba No need to use equals here. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-08 09:44:20 -06:00
Adam Treat
26cedb83b0 Use initializer lists instead of append where applicable. 
Signed-off-by: Adam Treat <treat.adam@gmail.com>
 2024-03-08 09:44:20 -06:00