Jared Van Bortel
03a9f0bedf
csharp: update C# bindings to work with GGUF ( #1651 )
2024-01-16 14:33:41 -05:00
Jared Van Bortel
f8564398fc
minor change to trigger CircleCI
2024-01-12 16:13:46 -05:00
Jared Van Bortel
b96406669d
CI: fix Windows Python build
2024-01-12 16:02:56 -05:00
Adam Treat
e51a504550
Add the new 2.6.1 release notes and bump the version.
2024-01-12 11:10:16 -05:00
Jared Van Bortel
eef604fd64
python: release bindings version 2.1.0
...
The backend has a breaking change for Falcon and MPT models, so we need
to make a new release.
2024-01-12 09:38:16 -05:00
Jared Van Bortel
b803d51586
restore network.h #include
...
The online installers need this.
2024-01-12 09:27:48 -05:00
Jared Van Bortel
7e9786fccf
chat: set search path early
...
This fixes the issues with installed versions of v2.6.0.
2024-01-11 12:04:18 -05:00
Adam Treat
f7aeeca884
Revert the release.
2024-01-10 10:41:33 -05:00
Adam Treat
16a84972f6
Bump to new version and right the release notes.
2024-01-10 10:21:45 -05:00
Jared Van Bortel
4dbe2634aa
models2.json: update models list for the next release
2024-01-10 09:18:31 -06:00
Adam Treat
233f0c4201
Bump the version for our next release.
2024-01-05 09:46:03 -05:00
AT
96cee4f9ac
Explicitly clear the kv cache each time we eval tokens to match n_past. ( #1808 )
2024-01-03 14:06:08 -05:00
ThiloteE
2d566710e5
Address review
2024-01-03 11:13:07 -06:00
ThiloteE
a0f7d7ae0e
Fix for "LLModel ERROR: Could not find CPU LLaMA implementation" v2
2024-01-03 11:13:07 -06:00
ThiloteE
38d81c14d0
Fixes https://github.com/nomic-ai/gpt4all/issues/1760 LLModel ERROR: Could not find CPU LLaMA implementation.
...
Inspired by Microsoft docs for LoadLibraryExA (https://learn.microsoft.com/en-us/windows/win32/api/libloaderapi/nf-libloaderapi-loadlibraryexa ).
When using LOAD_LIBRARY_SEARCH_DLL_LOAD_DIR, the lpFileName parameter must specify a fully qualified path, also it needs to be backslashes (\), not forward slashes (/).
2024-01-03 11:13:07 -06:00
Gerhard Stein
3e99b90c0b
Some cleanps
2024-01-03 08:41:40 -06:00
Daniel Salvatierra
c72c73a94f
app.py: add --device option for GPU support ( #1769 )
...
Signed-off-by: Daniel Salvatierra <dsalvat1@gmail.com>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
2023-12-20 16:01:03 -05:00
Cal Alaera
528eb1e7ad
Update server.cpp to return valid created timestamps ( #1763 )
...
Signed-off-by: Cal Alaera <59891537+CalAlaera@users.noreply.github.com>
2023-12-18 14:06:25 -05:00
Jared Van Bortel
d1c56b8b28
Implement configurable context length ( #1749 )
2023-12-16 17:58:15 -05:00
Jacob Nguyen
7aa0f779de
Update mkdocs.yml ( #1759 )
...
update doc routing
2023-12-15 13:37:29 -06:00
Jacob Nguyen
a1f27072c2
fix/macm1ts ( #1746 )
...
* make runtime library backend universal searchable
* corepack enable
* fix
* pass tests
* simpler
* add more jsdoc
* fix testS
* fix up circle ci
* bump version
* remove false positive warning
* add disclaimer
* update readme
* revert
* update ts docs
---------
Co-authored-by: Matthew Nguyen <matthewpnguyen@Matthews-MacBook-Pro-7.local>
2023-12-15 12:44:39 -06:00
Jared Van Bortel
3acbef14b7
fix AVX support by removing direct linking to AVX2 libs ( #1750 )
2023-12-13 12:11:09 -05:00
Jared Van Bortel
0600f551b3
chatllm: do not attempt to serialize incompatible state ( #1742 )
2023-12-12 11:45:03 -05:00
Jacob Nguyen
9481762802
Update continue_config.yml, shoudl fix ts docs failing ( #1743 )
2023-12-11 15:46:02 -05:00
Jared Van Bortel
778264fbab
python: don't use importlib as_file for a directory
...
The only reason to use as_file is to support copying a file from a
frozen package. We don't currently support this anyway, and as_file
isn't supported until Python 3.9, so get rid of it.
Fixes #1605
2023-12-11 13:35:56 -05:00
Jared Van Bortel
1df3da0a88
update llama.cpp for clang warning fix
2023-12-11 13:07:41 -05:00
aj-gameon
7facb8207b
docs: golang --recurse-submodules ( #1720 )
...
Co-authored-by: aj-gameon <aj@gameontechnology.com>
2023-12-11 12:58:58 -05:00
Jared Van Bortel
dfd8ef0186
backend: use ggml_new_graph for GGML backend v2 ( #1719 )
2023-12-06 14:38:53 -05:00
Adam Treat
fb3b1ceba2
Do not attempt to do a blocking retrieval if we don't have any collections.
2023-12-04 12:58:40 -05:00
Jared Van Bortel
9e28dfac9c
Update to latest llama.cpp ( #1706 )
2023-12-01 16:51:15 -05:00
Moritz Tim W
012f399639
fix typo ( #1697 )
2023-11-30 12:37:52 -05:00
Adam Treat
a328f9ed3f
Add a button to the collections dialog. Fix close button.
2023-11-22 09:10:44 -05:00
Adam Treat
e4ff972522
Bump and release v2.5.4
2023-11-21 16:56:52 -05:00
Adam Treat
4862e8b650
Networking retry on download error for models.
2023-11-21 16:30:18 -05:00
Jared Van Bortel
078c3bd85c
models2.json: add Orca 2 models ( #1672 )
2023-11-21 16:10:49 -05:00
AT
84749a4ced
Update gpt4all_chat.md
...
Signed-off-by: AT <manyoso@users.noreply.github.com>
2023-11-21 12:21:43 -05:00
AT
f1c58d0e2c
Update gpt4all_chat.md
...
Signed-off-by: AT <manyoso@users.noreply.github.com>
2023-11-21 11:55:14 -05:00
dsalvatierra
76413e1d03
Refactor engines module to fetch engine details
...
from API
Update chat.py
Signed-off-by: Daniel Salvatierra <dsalvat1@gmail.com>
2023-11-21 10:46:51 -05:00
dsalvatierra
db70f1752a
Update .gitignore and Dockerfile, add .env file
...
and modify test batch
2023-11-21 10:46:51 -05:00
dsalvat1
f3eaa33ce7
Fixing API problem - bin files are deprecated
2023-11-21 10:46:51 -05:00
Adam Treat
9e27a118ed
Fix system prompt.
2023-11-21 10:42:12 -05:00
Adam Treat
34555c4934
Bump version and release notes for v2.5.3
2023-11-20 10:26:35 -05:00
Adam Treat
9a3dd8815d
Fix GUI hang with localdocs by removing file system watcher in modellist.
2023-11-17 13:27:34 -05:00
Adam Treat
c1809a23ba
Fix text color on mac.
2023-11-17 11:59:31 -05:00
Adam Treat
59ed2a0bea
Use a global constant and remove a debug line.
2023-11-17 11:59:31 -05:00
Adam Treat
eecf351c64
Reduce copied code.
2023-11-17 11:59:31 -05:00
AT
abd4703c79
Update gpt4all-chat/embllm.cpp
...
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
Signed-off-by: AT <manyoso@users.noreply.github.com>
2023-11-17 11:59:31 -05:00
AT
4b413a60e4
Update gpt4all-chat/embeddings.cpp
...
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
Signed-off-by: AT <manyoso@users.noreply.github.com>
2023-11-17 11:59:31 -05:00
AT
17b346dfe7
Update gpt4all-chat/embeddings.cpp
...
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
Signed-off-by: AT <manyoso@users.noreply.github.com>
2023-11-17 11:59:31 -05:00
AT
71e37816cc
Update gpt4all-chat/qml/ModelDownloaderDialog.qml
...
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
Signed-off-by: AT <manyoso@users.noreply.github.com>
2023-11-17 11:59:31 -05:00