Commit Graph

2302 Commits

Author SHA1 Message Date
Ettore Di Giacinto
b10441a41c
ci: add pipelines for discord notifications (#2703)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-04 09:15:29 +02:00
LocalAI [bot]
97de2b6550
⬆️ Update ggerganov/llama.cpp (#2704)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-07-03 23:41:56 +00:00
LocalAI [bot]
497a037344
models(gallery): ⬆️ update checksum (#2701)
⬆️ Checksum updates in gallery/index.yaml

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-07-03 01:15:28 +00:00
LocalAI [bot]
cf0af16695
⬆️ Update ggerganov/llama.cpp (#2700)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-07-03 01:03:57 +00:00
LocalAI [bot]
62b4030278
⬆️ Update docs version mudler/LocalAI (#2699)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-07-03 00:22:53 +00:00
cryptk
c047c19145
fix: make sure the GNUMake jobserver is passed to cmake for the llama.cpp build (#2697)
Signed-off-by: Chris Jowett <421501+cryptk@users.noreply.github.com>
2024-07-02 08:46:59 +02:00
LocalAI [bot]
b941732f54
⬆️ Update ggerganov/llama.cpp (#2696)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-07-01 22:52:43 +02:00
Ettore Di Giacinto
e591ff2e74
fix(initializer): do select backends that exist (#2694)
we were not checking if the binary exists before picking these up from
the asset dir.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-01 22:50:36 +02:00
Ettore Di Giacinto
bd2f95c130
feat(backend): fallback with autodetect (#2693)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-07-01 18:11:04 +02:00
LocalAI [bot]
ad85c5a1e7
models(gallery): ⬆️ update checksum (#2690)
⬆️ Checksum updates in gallery/index.yaml

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-07-01 00:23:58 +00:00
LocalAI [bot]
421eb8a727
⬆️ Update ggerganov/llama.cpp (#2689)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-07-01 00:20:11 +00:00
Ettore Di Giacinto
b7ff441cc0
models(gallery): add llama3-turbcat-instruct-8b (#2687)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-30 14:40:01 +02:00
LocalAI [bot]
83d867ad46
⬆️ Update ggerganov/llama.cpp (#2683)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-30 01:51:51 +00:00
Ettore Di Giacinto
6acba2bcbe
models(gallery): add llm-compiler (#2684)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-29 23:32:01 +02:00
Ettore Di Giacinto
6a2a10603c
fix(talk): identify the model by ID instead of name (#2685)
This fixes a breakage in rendering the template. Now the models passed
by to the renderer have the ID field rather then Name

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-29 23:31:50 +02:00
Ettore Di Giacinto
356907a5cf
models(gallery): add llama3-8b-darkidol-2.1-uncensored-1048k-iq-imatrix (#2686)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-29 23:31:37 +02:00
Ettore Di Giacinto
7ab7a188d0
models(gallery): add bungo-l3-8b-iq-imatrix (#2682)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-29 22:05:27 +02:00
Ettore Di Giacinto
ff1a5bfc62
models(gallery): add l3-aethora-15b-v2 (#2679)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-29 11:33:00 +02:00
LocalAI [bot]
522f185baf
⬆️ Update docs version mudler/LocalAI (#2676)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-29 01:20:50 +00:00
LocalAI [bot]
f7b5a4ca7d
models(gallery): ⬆️ update checksum (#2678)
⬆️ Checksum updates in gallery/index.yaml

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-29 01:06:08 +00:00
LocalAI [bot]
1d30955677
⬆️ Update ggerganov/llama.cpp (#2677)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-29 00:43:02 +00:00
Ettore Di Giacinto
d3307e93d3
models(gallery): add new-dawn-llama (#2672)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-28 23:33:27 +02:00
LocalAI [bot]
8d9a452e4b
⬆️ Update ggerganov/llama.cpp (#2671)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-28 10:09:01 +02:00
Ettore Di Giacinto
466eb82845
ci: add latest tag for vulkan images
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-06-28 09:04:33 +02:00
LocalAI [bot]
7e562d10a3
⬆️ Update ggerganov/llama.cpp (#2652)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-28 01:30:37 +00:00
Ettore Di Giacinto
7b1e792732
deps(llama.cpp): bump to latest, update build variables (#2669)
* arrow_up: Update ggerganov/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* deps(llama.cpp): update build variables to follow upstream

Update build recipes with https://github.com/ggerganov/llama.cpp/pull/8006

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Disable shared libs by default in llama.cpp

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Disable shared libs in llama.cpp Makefile

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Disable metal embedding for now, until it is tested

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(mac): explicitly enable metal

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* debug

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix typo

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-27 23:10:04 +02:00
Ettore Di Giacinto
30b883affe
models(gallery): add gemma2-9b-it and gemma2-27b-it (#2670)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-27 23:08:22 +02:00
Tachi Koma
20ec4d0342
telegram-bot example: Update LocalAI version (fixes #2638) (#2640)
* Update LocalAI version for telegram-bot example (fixes #2638)

* Update examples/telegram-bot/docker-compose.yml

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>

---------

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-06-27 14:35:50 +02:00
Ettore Di Giacinto
a9f8460086
fix: typo in gallery model
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-06-27 08:54:13 +02:00
LocalAI [bot]
98b3b2b1ab
feat(swagger): update swagger (#2666)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-26 23:12:53 +00:00
Ettore Di Giacinto
e8bc0a789b
models(gallery): add arcee-spark (#2665)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-26 20:06:40 +02:00
Ettore Di Giacinto
2b6a2c7dde
models(gallery): add einstein v7 qwen2 (#2664)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-26 17:52:52 +02:00
Ettore Di Giacinto
c8c8238f9d
models(gallery): add dark-idol-1.2 (#2663)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-26 17:52:17 +02:00
Ettore Di Giacinto
3eaf59021c
feat(grammar): expose properties_order (#2662)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-26 14:59:02 +02:00
Ettore Di Giacinto
a8bfb6f9c2
feat(options): add repeat_last_n (#2660)
feat(options): add repeat_last_n

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-26 14:58:50 +02:00
Ettore Di Giacinto
b783c811db
feat(build): only build llama.cpp relevant targets (#2659)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-26 14:58:38 +02:00
Ettore Di Giacinto
59af0e77af
feat(ui): allow to select between all the available models in the chat (#2657)
feat(ui): let the chat to select from all the detected models

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-25 20:22:17 +02:00
Ettore Di Giacinto
5d83c8d3a2
Update quickstart.md
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-06-25 19:23:58 +02:00
Ettore Di Giacinto
8f968d0341
Update quickstart.md
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-06-25 19:18:43 +02:00
Ettore Di Giacinto
f93fe30350
ci: vulkan not ready for arm64 yet
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-06-25 18:11:57 +02:00
Ettore Di Giacinto
784ccf97ba
ci: adjust max-parallel
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-06-25 15:14:43 +02:00
LocalAI [bot]
a0163dafce
feat(swagger): update swagger (#2651)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-25 10:50:52 +02:00
Ettore Di Giacinto
f072cb3cd0
fix(cli): remove duplicate alias (#2654)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-25 10:08:13 +02:00
Ettore Di Giacinto
e84b31935c
feat(vulkan): add vulkan support to the llama.cpp backend (#2648)
feat(vulkan): add vulkan support to llama.cpp

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-24 20:04:58 +02:00
Ettore Di Giacinto
03b1cf51fd
feat(whisper): add translate option (#2649)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-24 19:21:22 +02:00
Ettore Di Giacinto
9e6dec0bc4 fix(install.sh): not all systems have nproc
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-24 18:21:20 +02:00
Ettore Di Giacinto
04b01cd62c ci: put a cap on parallel runs
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-24 18:08:09 +02:00
Ettore Di Giacinto
a181dd0ebc
refactor: gallery inconsistencies (#2647)
* refactor(gallery): move under core/

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(unarchive): do not allow symlinks

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-24 17:32:12 +02:00
Ettore Di Giacinto
69206fcd4b
fix(install.sh): move ARCH detection so it works also for mac (#2646)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-24 10:34:35 +02:00
Ettore Di Giacinto
2c94e15746
fix(install.sh): fix version typo (#2645)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-24 10:30:17 +02:00