6ca4d38a01
docs/examples: enhancements ( #1572 )
...
* docs: re-order sections
* fix references
* Add mixtral-instruct, tinyllama-chat, dolphin-2.5-mixtral-8x7b
* Fix link
* Minor corrections
* fix: models is a StringSlice, not a String
Signed-off-by: Ettore Di Giacinto <mudler@localai.io >
* WIP: switch docs theme
* content
* Fix GH link
* enhancements
* enhancements
* Fixed how to link
Signed-off-by: lunamidori5 <118759930+lunamidori5@users.noreply.github.com >
* fixups
* logo fix
* more fixups
* final touches
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io >
Signed-off-by: lunamidori5 <118759930+lunamidori5@users.noreply.github.com >
Co-authored-by: lunamidori5 <118759930+lunamidori5@users.noreply.github.com >
2024-01-18 19:41:08 +01:00
b5c93f176a
⬆️ Update ggerganov/llama.cpp ( #1599 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-18 14:39:30 +01:00
1aaf88098d
⬆️ Update ggerganov/llama.cpp ( #1597 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-17 09:27:02 +01:00
6f447e613d
docs: missing golang requirement for local build for debian ( #1596 )
...
docs: fix missing golang requirement for local build for debian
2024-01-17 09:26:43 +01:00
dfb7c3b1aa
⬆️ Update ggerganov/llama.cpp ( #1594 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-16 14:47:57 +01:00
b41eb5e1f3
prepend built binaries in PATH for BUILD_GRPC_FOR_BACKEND_LLAMA ( #1593 )
...
prepend built binaries in PATH
2024-01-16 14:47:47 +01:00
9c2d264979
⬆️ Update ggerganov/llama.cpp ( #1590 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-15 09:01:07 +01:00
b996c3198c
⬆️ Update ggerganov/llama.cpp ( #1587 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-14 09:46:47 +00:00
f879c07c86
Update README.md
...
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2024-01-14 10:00:46 +01:00
441e2965ff
move BUILD_GRPC_FOR_BACKEND_LLAMA logic to makefile: errors in this section now immediately fail the build ( #1576 )
...
* move BUILD_GRPC_FOR_BACKEND_LLAMA option to makefile
* review: oversight, fixup cmake_args
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
Signed-off-by: Dionysius <1341084+dionysius@users.noreply.github.com >
---------
Signed-off-by: Dionysius <1341084+dionysius@users.noreply.github.com >
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2024-01-13 10:08:26 +01:00
cbe9a03e3c
⬆️ Update ggerganov/llama.cpp ( #1583 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-12 23:04:04 +01:00
4ee7e73d00
⬆️ Update ggerganov/llama.cpp ( #1578 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-12 16:04:33 +01:00
1cca449726
Moving the how tos to self hosted ( #1574 )
...
* Update _index.md
Signed-off-by: lunamidori5 <118759930+lunamidori5@users.noreply.github.com >
* Delete docs/content/howtos/easy-setup-sd.md
Signed-off-by: lunamidori5 <118759930+lunamidori5@users.noreply.github.com >
* Delete docs/content/howtos/easy-setup-full.md
Signed-off-by: lunamidori5 <118759930+lunamidori5@users.noreply.github.com >
* Delete docs/content/howtos/easy-setup-embeddings.md
Signed-off-by: lunamidori5 <118759930+lunamidori5@users.noreply.github.com >
* Delete docs/content/howtos/easy-setup-docker.md
Signed-off-by: lunamidori5 <118759930+lunamidori5@users.noreply.github.com >
* Delete docs/content/howtos/easy-request.md
Signed-off-by: lunamidori5 <118759930+lunamidori5@users.noreply.github.com >
* Delete docs/content/howtos/easy-model.md
Signed-off-by: lunamidori5 <118759930+lunamidori5@users.noreply.github.com >
* Update _index.en.md
Signed-off-by: lunamidori5 <118759930+lunamidori5@users.noreply.github.com >
* Update README.md
Signed-off-by: lunamidori5 <118759930+lunamidori5@users.noreply.github.com >
* Delete docs/content/howtos directory
Signed-off-by: lunamidori5 <118759930+lunamidori5@users.noreply.github.com >
---------
Signed-off-by: lunamidori5 <118759930+lunamidori5@users.noreply.github.com >
2024-01-11 09:25:18 +01:00
faf7c1c325
⬆️ Update ggerganov/llama.cpp ( #1573 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-11 08:41:32 +01:00
58288494d6
⬆️ Update ggerganov/llama.cpp ( #1568 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-10 10:18:57 +01:00
72283dc744
minor: replace shell pwd in Makefile with CURDIR for better windows compatibility ( #1571 )
...
replace shell pwd in Makefile with CURDIR
2024-01-10 08:39:50 +00:00
b8240b4c18
⬆️ Update docs version mudler/LocalAI ( #1567 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-09 21:56:12 +01:00
5309da40b7
Update Dockerfile
...
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2024-01-09 08:55:43 +01:00
08b90b4720
Update _index.en.md
...
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2024-01-09 08:50:19 +01:00
2e890b3838
⬆️ Update ggerganov/llama.cpp ( #1563 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-09 08:48:40 +01:00
06656fc057
⬆️ Update docs version mudler/LocalAI ( #1562 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-09 08:48:24 +01:00
574fa67bdc
⬆️ Update ggerganov/llama.cpp ( #1558 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-08 00:38:03 +01:00
e19d7226f8
feat: more embedded models, coqui fixes, add model usage and description ( #1556 )
...
* feat: add model descriptions and usage
* remove default model gallery
* models: add embeddings and tts
* docs: update table
* docs: updates
* images: cleanup pip cache after install
* images: always run apt-get clean
* ux: improve gRPC connection errors
* ux: improve some messages
* fix: fix coqui when no AudioPath is passed by
* embedded: add more models
* Add usage
* Reorder table
2024-01-08 00:37:02 +01:00
0843fe6c65
⬆️ Update docs version mudler/LocalAI ( #1557 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-07 09:36:21 +01:00
62a02cd1fe
deps(conda): use transformers environment with autogptq ( #1555 )
2024-01-06 15:30:53 +01:00
949da7792d
deps(conda): use transformers-env with vllm,exllama(2) ( #1554 )
...
* deps(conda): use transformers with vllm
* join vllm, exllama, exllama2, split petals
2024-01-06 13:32:28 +01:00
ce724a7e55
docs: improve getting started ( #1553 )
...
* docs: improve getting started
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
* cleanups
* Use dockerhub links
* Shrink command to minimum
---------
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2024-01-06 01:04:14 +01:00
0a06c80801
⬆️ Update ggerganov/llama.cpp ( #1547 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-05 23:27:51 +01:00
edc55ade61
⬆️ Update docs version mudler/LocalAI ( #1546 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
Co-authored-by: lunamidori5 <118759930+lunamidori5@users.noreply.github.com >
2024-01-05 23:27:30 +01:00
09e5d9007b
feat: embedded model configurations, add popular model examples, refactoring ( #1532 )
...
* move downloader out
* separate startup functions for preloading configuration files
* docs: add popular model examples
Signed-off-by: Ettore Di Giacinto <mudler@localai.io >
* shorteners
* Add llava
* Add mistral-openorca
* Better link to build section
* docs: update
* fixup
* Drop code dups
* Minor fixups
* Apply suggestions from code review
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
* ci: try to cache gRPC build during tests
Signed-off-by: Ettore Di Giacinto <mudler@localai.io >
* ci: do not build all images for tests, just necessary
* ci: cache gRPC also in release pipeline
* fixes
* Update model_preload_test.go
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io >
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2024-01-05 23:16:33 +01:00
db926896bd
Revert "[Refactor]: Core/API Split" ( #1550 )
...
Revert "[Refactor]: Core/API Split (#1506 )"
This reverts commit ab7b4d5ee9
2024-01-05 18:04:46 +01:00
ab7b4d5ee9
[Refactor]: Core/API Split ( #1506 )
...
Refactors api folder to core, creates firm split between backend code and api frontend.
2024-01-05 15:34:56 +01:00
bcf02449b3
ci(dockerhub): push images also to dockerhub ( #1542 )
...
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2024-01-04 08:32:29 +01:00
d48faf35ab
⬆️ Update ggerganov/llama.cpp ( #1544 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-04 00:08:03 +01:00
583bd28a5c
fix(diffusers): add omegaconf dependency ( #1540 )
...
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2024-01-04 00:06:41 +01:00
7e1d8c489b
⬆️ Update ggerganov/llama.cpp ( #1533 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-03 08:43:35 +01:00
de28867374
⬆️ Update ggerganov/llama.cpp ( #1531 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2024-01-02 00:28:22 +00:00
a1aa6cb7c2
fix(entrypoint): cd to backend dir before start ( #1530 )
...
Certain backends as vall-e-x are not meant to be used as a library, so
we want to start the process in the same folder where the backend and
all the assets are fixes #1394
2024-01-01 22:02:48 +01:00
85e2767dca
feat: add trimsuffix ( #1528 )
2024-01-01 14:39:42 +01:00
fd48cb6506
deps(llama.cpp): update and sync grpc server ( #1527 )
...
Signed-off-by: Ettore Di Giacinto <mudler@localai.io >
2024-01-01 14:39:31 +01:00
522659eb59
feat(prepare): allow to specify additional files to download ( #1526 )
2024-01-01 14:39:13 +01:00
f068efe509
docs(phi-2): add example ( #1525 )
2024-01-01 10:51:47 +01:00
726fe416bb
docs: update hot topics
...
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2024-01-01 10:41:39 +01:00
66fa4f1767
feat: share models by url ( #1522 )
...
* feat: allow to pass by models via args
* expose it also as an env/arg
* docs: enhancements to build/requirements
* do not display status always
* print download status
* not all mesages are debug
2024-01-01 10:31:03 +01:00
d6565f3b99
Update _index.en.md
...
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com >
2023-12-31 10:58:22 +01:00
27686ff20b
⬆️ Update ggerganov/llama.cpp ( #1518 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2023-12-31 00:19:08 +00:00
a8b865022f
⬆️ Update docs version mudler/LocalAI ( #1517 )
...
Signed-off-by: GitHub <noreply@github.com >
Co-authored-by: mudler <mudler@users.noreply.github.com >
2023-12-30 23:50:24 +00:00
c1888a8062
feat(preload): prepare models in galleries ( #1515 )
...
Previously if applying models from the gallery API, we didn't actually
allowed remote URLs as models as nothing was actually downloading the
models referenced in the configuration file. Now we call Preload after
we have all the models loaded in memory.
2023-12-30 18:55:18 +01:00
a95bb0521d
fix(download): correctly check for not found error ( #1514 )
2023-12-30 15:36:46 +01:00
e2311a145c
Fix: Set proper Homebrew install location for x86 Macs ( #1510 )
...
* set proper Homebrew install location for x86 Macs
* fix: remove prior conditional that my logic replaces
2023-12-30 12:37:26 +01:00
