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
1,497 Commits 491 Branches 56 Tags 46 MiB
7e5e84fbb7
Commit Graph

1497 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
AMOGUS
5f0aaf8bdb python binding's TopP also needs some love 
Changed the Python binding's TopP from 0.1 to 0.4

Signed-off-by: AMOGUS <137312610+Amogus8P@users.noreply.github.com>
 2023-07-19 10:36:23 -04:00
AMOGUS
4974ae917c Update default TopP to 0.4 
TopP 0.1 was found to be somewhat too aggressive, so a more moderate default of 0.4 would be better suited for general use.

Signed-off-by: AMOGUS <137312610+Amogus8P@users.noreply.github.com>
 2023-07-19 10:36:23 -04:00
cosmic-snow
63849d9afc Add AVX/AVX2 requirement to main README.md 
Signed-off-by: cosmic-snow <134004613+cosmic-snow@users.noreply.github.com>
 2023-07-19 13:05:42 +02:00
cosmic-snow
2d02c65177
Handle edge cases when generating embeddings (#1215) 
* Handle edge cases when generating embeddings
* Improve Python handling & add llmodel_c.h note
- In the Python bindings fail fast with a ValueError when text is empty
- Advice other bindings authors to do likewise in llmodel_c.h
 2023-07-17 13:21:03 -07:00
Felix Zaslavskiy
1e74171a7b
Java binding - Improve error check before loading Model file (#1206) 
* Javav binding - Add check for Model file be Readable.

* add todo for java binding.

---------

Co-authored-by: Feliks Zaslavskiy <feliks.zaslavskiy@optum.com>
Co-authored-by: felix <felix@zaslavskiy.net>
 2023-07-15 18:07:42 -04:00
Andriy Mulyar
cfd70b69fc
Update gpt4all_python_embedding.md 
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
 2023-07-14 14:54:56 -04:00
Andriy Mulyar
306105e62f
Update gpt4all_python_embedding.md 
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
 2023-07-14 14:54:36 -04:00
Andriy Mulyar
89e277bb3c
Update gpt4all_python_embedding.md 
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
 2023-07-14 14:30:14 -04:00
Adam Treat
f543affa9a Add better docs and threading support to bert. 2023-07-14 14:14:22 -04:00
Lakshay Kansal
6c8669cad3 highlighting rules for html and php and latex 2023-07-14 11:36:01 -04:00
Adam Treat
0c0a4f2c22 Add the docs. 2023-07-14 10:48:18 -04:00
Adam Treat
6656f0f41e Fix the test to work and not do timings. 2023-07-14 09:48:57 -04:00
Adam Treat
bb2b82e1b9 Add docs and bump version since we changed python api again. 2023-07-14 09:48:57 -04:00
Aaron Miller
c77ab849c0 LLModel objects should hold a reference to the library 
prevents llmodel lib from being gc'd before live model objects
 2023-07-14 09:48:57 -04:00
Aaron Miller
1c4a244291 bump mem allocation a bit 2023-07-14 09:48:57 -04:00
Aaron Miller
936dcd2bfc use default n_threads 2023-07-14 09:48:57 -04:00
Aaron Miller
15f1fe5445 rename embedder 2023-07-14 09:48:57 -04:00
Adam Treat
ee4186d579 Fixup bert python bindings. 2023-07-14 09:48:57 -04:00
cosmic-snow
6200900677
Fix Windows MSVC arch detection (#1194) 
- in llmodel.cpp to fix AVX-only handling

Signed-off-by: cosmic-snow <134004613+cosmic-snow@users.noreply.github.com>
 2023-07-13 14:44:17 -04:00
Adam Treat
4963db8f43 Bump the version numbers for both python and c backend. 2023-07-13 14:21:46 -04:00
Adam Treat
0efdbfcffe Bert 2023-07-13 14:21:46 -04:00
Adam Treat
315a1f2aa2 Move it back as internal class. 2023-07-13 14:21:46 -04:00
Adam Treat
ae8eb297ac Add sbert backend. 2023-07-13 14:21:46 -04:00
Adam Treat
1f749d7633 Clean up backend code a bit and hide impl. details. 2023-07-13 14:21:46 -04:00
Adam Treat
33557b1f39 Move the implementation out of llmodel class. 2023-07-13 14:21:46 -04:00
Adam Treat
64b409e0b8 keep trying 2023-07-13 13:57:22 -04:00
Adam Treat
e59946f05d try again to unbreak circleci 2023-07-13 13:55:22 -04:00
Adam Treat
b72b409d40 try again to unbreak circlci 2023-07-13 13:52:55 -04:00
Adam Treat
59cae1132c Try and unbreak circleci. 2023-07-13 13:45:47 -04:00
Adam Treat
a0dae86a95 Add bert to models.json 2023-07-13 13:37:12 -04:00
AT
18ca8901f0
Update README.md 
Signed-off-by: AT <manyoso@users.noreply.github.com>
 2023-07-12 16:30:56 -04:00
cosmic-snow
00a945eaee Update gpt4all_faq.md 
- Add information about AVX/AVX2.
- Update supported architectures.

Signed-off-by: cosmic-snow <134004613+cosmic-snow@users.noreply.github.com>
 2023-07-12 15:19:26 -04:00
Zach Nussbaum
6c4f449b7a
fix: update train scripts and configs for other models (#1164) 
* feat: falcon config

* feat: mpt config

* chore: gitignore

* refactor: step calculation

* fix: attention mask + shuffle on epoch end

* fix: return tensors

* fix: wait for everyone

* chore: config

* chore: ds config

* fix: remove ccols

* fix: logging and saving

* chore: add einops
 2023-07-12 15:18:24 -04:00
Adam Treat
e8b19b8e82 Bump version to 2.4.14 and provide release notes. 2023-07-12 14:58:45 -04:00
Adam Treat
8eb0844277 Check if the trimmed version is empty. 2023-07-12 14:31:43 -04:00
Adam Treat
be395c12cc Make all system prompts empty by default if model does not include in training data. 2023-07-12 14:31:43 -04:00
Aaron Miller
6a8fa27c8d Correctly find models in subdirs of model dir 
QDirIterator doesn't seem particular subdir aware, its path() returns
the iterated dir. This was the simplest way I found to get this right.
 2023-07-12 14:18:40 -04:00
Adam Treat
8893db5896 Add wizard model and rename orca to be more specific. 2023-07-12 14:12:46 -04:00
Adam Treat
60627bd41f Prefer 7b models in order of default model load. 2023-07-12 12:50:18 -04:00
Aaron Miller
5df4f1bf8c codespell 2023-07-12 12:49:06 -04:00
Aaron Miller
10ca2c4475 center the spinner 2023-07-12 12:49:06 -04:00
Adam Treat
e9897518d1 Show busy if models.json download taking longer than expected. 2023-07-12 12:49:06 -04:00
Aaron Miller
432b7ebbd7 include windows.h just to be safe 2023-07-12 12:46:46 -04:00
Aaron Miller
95b8fb312e windows/msvc: use high level processor feature detection API 
see https://learn.microsoft.com/en-us/windows/win32/api/processthreadsapi/nf-processthreadsapi-isprocessorfeaturepresent
 2023-07-12 12:46:46 -04:00
Aaron Miller
ad0e7fd01f chatgpt: ensure no extra newline in header 2023-07-12 10:53:25 -04:00
Aaron Miller
f0faa23ad5
cmakelists: always export build commands (#1179) 
friendly for using editors with clangd integration that don't also
manage the build themselves
 2023-07-12 10:49:24 -04:00
Adam Treat
0d726b22b8 When we explicitly cancel an operation we shouldn't throw an error. 2023-07-12 10:34:10 -04:00
Adam Treat
13b2d47be5 Provide an error dialog if for any reason we can't access the settings file. 2023-07-12 08:50:21 -04:00
Adam Treat
e9d42fba35 Don't show first start more than once. 2023-07-11 18:54:53 -04:00
mvenditto
8a31239e90 bump version 2023-07-11 18:09:39 -04:00