AT
ea1ade8668
Use different language for prompt size too large. ( #3004 )
...
Signed-off-by: Adam Treat <treat.adam@gmail.com>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
2024-09-27 12:29:22 -04:00
Jared Van Bortel
f9d6be8afb
backend: rebase llama.cpp on upstream as of Sep 26th ( #2998 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-09-27 12:05:59 -04:00
Max Cembalest
117a8e7faa
Docs section & page for the GPT4All API server ( #2990 )
...
Signed-off-by: Max Cembalest <mbcembalest@gmail.com>
2024-09-26 11:07:49 -04:00
Andriy Mulyar
a2b4529945
docs: add link to YouTube video tutorial ( #2954 )
...
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
2024-09-12 11:38:08 -04:00
Jared Van Bortel
46314dc7f3
python: warn if Microsoft Visual C++ runtime libs are not found ( #2920 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-08-30 12:54:20 -04:00
Jared Van Bortel
bd044bef27
repo: use the new GPT4All website URL ( #2915 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-08-26 16:27:41 -04:00
Simon Willison
7073fe341f
Add Changelog to links on PyPI ( #2860 )
...
Signed-off-by: Simon Willison <swillison@gmail.com>
2024-08-14 16:28:04 -04:00
Jared Van Bortel
b99ca17a7d
python: fix missing link in changelog
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-08-14 14:22:12 -04:00
Jared Van Bortel
a232befa58
python: fix py3.8 compat ( #2871 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-08-14 13:30:14 -04:00
Jared Van Bortel
af9416c0bf
python: fix CUDA dependency version ( #2858 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-08-13 19:11:04 -04:00
Jared Van Bortel
3ba9c6344d
python: release version 2.8.1 ( #2857 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-08-13 17:12:34 -04:00
Jared Van Bortel
6518b33697
llamamodel: use greedy sampling when temp=0 ( #2854 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-08-13 17:04:50 -04:00
Jared Van Bortel
971c83d1d3
llama.cpp: pull in fix for Kompute-related nvidia-egl crash ( #2843 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-08-13 11:10:10 -04:00
Jared Van Bortel
be91576937
ci: use consistent build options on macOS ( #2849 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-08-12 19:03:18 -04:00
Jared Van Bortel
c950fdd84e
changelogs: add PR 2781 ( #2809 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-08-07 18:59:57 -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
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
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
patcher9
71c957f8ee
Update monitoring.md ( #2724 )
...
Signed-off-by: patcher9 <patcher99@dokulabs.com>
2024-07-25 19:13:00 -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
mcembalest
62abecaec8
fixed link to embeddings docs on localdocs page ( #2687 )
...
Signed-off-by: Max Cembalest <mbcembalest@gmail.com>
2024-07-17 16:36:31 -04:00
akgom
214499ce84
Update use-local-ai-models-to-privately-chat-with-google-drive.md ( #2647 )
...
Updated screenshots for google drive guide with new app images
Signed off by Max Cembalest
2024-07-11 13:22:43 -04:00
akgom
df5d374187
Update use-local-ai-models-to-privately-chat-with-One-Drive.md ( #2646 )
...
Signed-off-by: akgom <132290469+akgom@users.noreply.github.com>
2024-07-11 11:26:28 -04:00
akgom
7ec67eab15
Create using-local-ai-models-to-privately-chat-with-One-Drive.md ( #2637 )
...
* Create using-local-ai-models-to-privately-chat-with-One-Drive.md
Signed-off-by: Max Cembalest
2024-07-11 11:03:05 -04:00
Andriy Mulyar
d87484d3c9
analytics entry ( #2641 )
...
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
2024-07-10 18:50:16 -04:00
mcembalest
0de6eba69e
formatted note callouts ( #2633 )
...
Signed-off-by: Max Cembalest <mbcembalest@gmail.com>
2024-07-10 09:55:53 -04:00
Andriy Mulyar
62d423c554
typo ( #2629 )
...
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
2024-07-09 22:54:43 -04:00
akgom
7f2ceff5c8
Create googledrive.md ( #2621 )
...
* Create googledrive.md
Signed-off-by: akgom <132290469+akgom@users.noreply.github.com>
* updates
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
---------
Signed-off-by: akgom <132290469+akgom@users.noreply.github.com>
Signed-off-by: Andriy Mulyar <andriy.mulyar@gmail.com>
Co-authored-by: Andriy Mulyar <andriy.mulyar@gmail.com>
2024-07-09 22:47:23 -04:00
Hampus
b9103892b6
fix: incomplete sentence in faq ( #2611 )
...
Signed-off-by: Hampus <16954508+xdHampus@users.noreply.github.com>
2024-07-09 11:13:03 -04:00
HydeZero
c73f0e5c8c
python: fix docstring grammar ( #2529 )
...
Signed-off-by: HydeZero <128327411+HydeZero@users.noreply.github.com>
2024-07-05 12:44:28 -04:00
mcembalest
69102a2859
small edits and placeholder gif ( #2513 )
...
* small edits and placeholder gif
Signed-off-by: Max Cembalest <max@nomic.ai>
* jul2 docs updates
Signed-off-by: Max Cembalest <max@nomic.ai>
* added video
Signed-off-by: mcembalest <70534565+mcembalest@users.noreply.github.com>
Signed-off-by: Max Cembalest <max@nomic.ai>
* quantization nits
Signed-off-by: Max Cembalest <max@nomic.ai>
---------
Signed-off-by: Max Cembalest <max@nomic.ai>
Signed-off-by: mcembalest <70534565+mcembalest@users.noreply.github.com>
2024-07-02 11:41:39 -04:00
mcembalest
b85b74d5bf
docs: bump copyright year and change site_description ( #2502 )
...
Signed-off-by: Max Cembalest <max@nomic.ai>
2024-07-01 14:34:07 -04:00
mcembalest
5306595176
V3 docs max ( #2488 )
...
* new skeleton
Signed-off-by: Max Cembalest <max@nomic.ai>
* v3 docs
Signed-off-by: Max Cembalest <max@nomic.ai>
---------
Signed-off-by: Max Cembalest <max@nomic.ai>
2024-07-01 13:00:14 -04:00
Jared Van Bortel
01870b4a46
chat: fix blank device in UI and improve Mixpanel reporting ( #2409 )
...
Also remove LLModel::hasGPUDevice.
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-06-26 15:26:27 -04:00
patcher9
986d9d9bb8
docs: add description of OpenLIT GPU monitoring ( #2436 )
...
Signed-off-by: patcher9 <patcher99@dokulabs.com>
2024-06-13 11:23:32 -04:00
patcher9
d43bfa0a53
docs: document OpenLIT integration ( #2386 )
...
Signed-off-by: patcher9 <patcher99@dokulabs.com>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>
2024-06-05 11:05:21 -04:00
woheller69
f001897a1a
Fix path in Readme ( #2339 )
...
Signed-off-by: woheller69 <68678880+woheller69@users.noreply.github.com>
2024-05-31 17:20:41 -04:00
Jared Van Bortel
09dd3dc318
python: depend on offical NVIDIA CUDA packages ( #2355 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-05-20 18:06:27 -04:00
Jared Van Bortel
c779d8a32d
python: init_gpu fixes ( #2368 )
...
* python: tweak GPU init failure message
* llama.cpp: update submodule for use-after-free fix
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-05-20 18:04:11 -04:00
Jared Van Bortel
d2a99d9bc6
support the llama.cpp CUDA backend ( #2310 )
...
* rebase onto llama.cpp commit ggerganov/llama.cpp@d46dbc76f
* support for CUDA backend (enabled by default)
* partial support for Occam's Vulkan backend (disabled by default)
* partial support for HIP/ROCm backend (disabled by default)
* sync llama.cpp.cmake with upstream llama.cpp CMakeLists.txt
* changes to GPT4All backend, bindings, and chat UI to handle choice of llama.cpp backend (Kompute or CUDA)
* ship CUDA runtime with installed version
* make device selection in the UI on macOS actually do something
* model whitelist: remove dbrx, mamba, persimmon, plamo; add internlm and starcoder2
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-05-15 15:27:50 -04:00
Jared Van Bortel
86560f3952
maint: remove Docker API server and related references ( #2314 )
...
Signed-off-by: Jared Van Bortel <jared@nomic.ai>
2024-05-09 12:50:26 -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
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
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
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
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
