ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-03-23 04:25:32 +00:00
Code Issues Actions13 Packages Projects Releases Wiki Activity
3,678 Commits 51 Branches 110 Tags
90a7451da4
Commit Graph

3678 Commits

Author SHA1 Message Date
Ettore Di Giacinto
90a7451da4
chore(model gallery): add allura-org_bigger-body-70b () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-15 14:43:51 +01:00
LocalAI [bot]
529a4b9ee8
chore: ⬆️ Update ggml-org/llama.cpp to 9f2250ba722738ec0e6ab684636268a79160c854 () 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-03-14 21:45:54 +00:00
Ettore Di Giacinto
0567e104eb
chore(model gallery): add eurollm-9b-instruct () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-14 09:25:44 +01:00
Ettore Di Giacinto
ecbeacd022
chore(model gallery): add prithivmlmods_viper-coder-32b-elite13 () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-14 09:20:27 +01:00
Ettore Di Giacinto
2772960e41
chore(model gallery): add nousresearch_deephermes-3-llama-3-3b-preview () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-14 09:16:17 +01:00
Ettore Di Giacinto
1b694191e2
chore(model gallery): add nousresearch_deephermes-3-mistral-24b-preview () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-14 09:13:27 +01:00
Ettore Di Giacinto
69578a5f8f
chore(model gallery): add models/qgallouedec_gemma-3-27b-it-codeforces-sft () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-14 09:11:13 +01:00
LocalAI [bot]
7d96cfe72b
chore: ⬆️ Update ggml-org/llama.cpp to 84d547554123a62e9ac77107cb20e4f6cc503af4 () 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-03-13 22:30:17 +00:00
Ettore Di Giacinto
423514a5a5
fix(clip): do not imply GPU offload by default () 
* fix(clip): do not imply GPUs by default

Until a better solution is found upstream, be conservative and default
to GPU.

https://github.com/ggml-org/llama.cpp/pull/12322
https://github.com/ggml-org/llama.cpp/pull/12322#issuecomment-2720970695

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

* allow to override gpu via backend options

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-13 15:14:11 +01:00
Ettore Di Giacinto
12568c7d6d
chore(model gallery): add gemma-3-1b-it () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-13 09:48:40 +01:00
Ettore Di Giacinto
8d16a0a536
chore(model gallery): add gemma-3-4b-it () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-13 09:47:01 +01:00
Ettore Di Giacinto
87ca801f00
chore(model gallery): add gemma-3-12b-it () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-13 09:44:49 +01:00
Ettore Di Giacinto
e4ecbb6c30
chore(model gallery): add gemma-3-27b-it () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-13 08:28:28 +01:00
LocalAI [bot]
b1a67de2b9
chore: ⬆️ Update ggml-org/llama.cpp to f08f4b3187b691bb08a8884ed39ebaa94e956707 () 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-03-13 01:01:30 +00:00
LocalAI [bot]
71a23910fe
chore: ⬆️ Update ggml-org/llama.cpp to 80a02aa8588ef167d616f76f1781b104c245ace0 () 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-03-12 16:26:09 +00:00
LocalAI [bot]
0ede31f9cf
chore: ⬆️ Update ggml-org/llama.cpp to 10f2e81809bbb69ecfe64fc8b4686285f84b0c07 () 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-03-12 14:13:04 +00:00
Ettore Di Giacinto
9f5dcf2d1e
feat(aio): update AIO image defaults () 
* feat(aio): update AIO image defaults

cpu:
 - text-to-text: llama3.1
 - embeddings: granite-embeddings
 - vision: moonream2

gpu/intel:
 - text-to-text: localai-functioncall-qwen2.5-7b-v0.5
 - embeddings: granite-embeddings
 - vision: minicpm

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

* feat(aio): use minicpm as moondream2 stopped working

https://github.com/ggml-org/llama.cpp/pull/12322#issuecomment-2717483759

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-12 12:55:06 +01:00
Ettore Di Giacinto
e878556e98
chore(model gallery): add trashpanda-org_qwq-32b-snowdrop-v0 () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-12 08:26:09 +01:00
Ettore Di Giacinto
b096928172
chore(model gallery): add open-r1_olympiccoder-7b () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-12 08:24:35 +01:00
Ettore Di Giacinto
db7442ae67
chore(model gallery): add open-r1_olympiccoder-32b () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-12 08:23:01 +01:00
Ettore Di Giacinto
b6cd430e08
chore(model gallery): add thedrummer_gemmasutra-small-4b-v1 () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-12 08:19:51 +01:00
LocalAI [bot]
478e50cda2
chore: ⬆️ Update ggml-org/llama.cpp to 2c9f833d17bb5b8ea89dec663b072b5420fc5438 () 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2025-03-11 11:19:03 +00:00
Ettore Di Giacinto
1db2b9943c
chore(deps): Bump grpcio to 1.71.0 () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-11 09:44:21 +01:00
Ettore Di Giacinto
ac41aa8b67
chore(model gallery): add openpipe_deductive-reasoning-qwen-32b () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-11 09:44:07 +01:00
Ettore Di Giacinto
156a98e2e7
chore(model gallery): add openpipe_deductive-reasoning-qwen-14b () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-11 09:40:38 +01:00
dependabot[bot]
d88ec1209e
chore(deps): Bump docs/themes/hugo-theme-relearn from 4a4b60e to 9a020e7 () 
chore(deps): Bump docs/themes/hugo-theme-relearn

Bumps [docs/themes/hugo-theme-relearn](https://github.com/McShelby/hugo-theme-relearn) from `4a4b60e` to `9a020e7`.
- [Release notes](https://github.com/McShelby/hugo-theme-relearn/releases)
- [Commits](4a4b60ef04...9a020e7ead)

---
updated-dependencies:
- dependency-name: docs/themes/hugo-theme-relearn
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-03-11 09:39:04 +01:00
dependabot[bot]
fde8dbfc80
chore(deps): Bump appleboy/ssh-action from 1.2.1 to 1.2.2 () 
Bumps [appleboy/ssh-action](https://github.com/appleboy/ssh-action) from 1.2.1 to 1.2.2.
- [Release notes](https://github.com/appleboy/ssh-action/releases)
- [Changelog](https://github.com/appleboy/ssh-action/blob/master/.goreleaser.yaml)
- [Commits](https://github.com/appleboy/ssh-action/compare/v1.2.1...v1.2.2)

---
updated-dependencies:
- dependency-name: appleboy/ssh-action
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-03-11 08:29:31 +01:00
Ettore Di Giacinto
879dc73eba
Revert "chore(deps): Bump intel-extension-for-pytorch from 2.3.110+xpu to 2.6.10+xpu in /backend/python/diffusers" () 
Revert "chore(deps): Bump intel-extension-for-pytorch from 2.3.110+xpu to 2.6…"

This reverts commit 1dfc52de161ef2cb64a1435d24b389aae6d93ff1.
 2025-03-11 08:29:05 +01:00
dependabot[bot]
1dfc52de16
chore(deps): Bump intel-extension-for-pytorch from 2.3.110+xpu to 2.6.10+xpu in /backend/python/diffusers () 
chore(deps): Bump intel-extension-for-pytorch

Bumps intel-extension-for-pytorch from 2.3.110+xpu to 2.6.10+xpu.

---
updated-dependencies:
- dependency-name: intel-extension-for-pytorch
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2025-03-10 21:14:43 +00:00
Ettore Di Giacinto
1331129485
fix(routes): do not gate generated artifacts via key () 
fix(routes): do not gate generated images via key

We generate unique uris for images.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-10 15:58:25 +01:00
Ettore Di Giacinto
1cd98062e5
chore(model gallery): add hyperllama3.1-v2-i1 () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-10 10:52:36 +01:00
Ettore Di Giacinto
9791d9b77a
chore(model gallery): add opencrystal-l3-15b-v2.1-i1 () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-10 10:50:02 +01:00
Ettore Di Giacinto
8956452a45
chore(model gallery): add llmevollama-3.1-8b-v0.1-i1 () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-10 10:46:49 +01:00
LocalAI [bot]
f3659fa49c
chore: ⬆️ Update ggml-org/llama.cpp to 1e2f78a00450593e2dfa458796fcdd9987300dfc () 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-03-09 21:44:52 +00:00
Ettore Di Giacinto
585f2be793
chore(model gallery): add tower-babel_babel-9b-chat () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-09 12:09:56 +01:00
LocalAI [bot]
d13f160222
chore: ⬆️ Update ggml-org/llama.cpp to 0fd7ca7a210bd4abc995cd728491043491dbdef7 () 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-03-08 21:41:26 +00:00
Ettore Di Giacinto
db5495b9d7
chore(model gallery): add goppa-ai_goppa-logillama () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-08 11:37:40 +01:00
Ettore Di Giacinto
3def1ae232
chore(model gallery): add huihui-ai_qwq-32b-abliterated () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-08 11:34:37 +01:00
Ettore Di Giacinto
c6ebead8e5
chore(model gallery): add steelskull_l3.3-electra-r1-70b () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-08 11:23:42 +01:00
LocalAI [bot]
cff4a950e0
chore: ⬆️ Update ggml-org/llama.cpp to 7ab364390f92b0b8d83f69821a536b424838f3f8 () 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-03-07 22:54:28 +00:00
Ettore Di Giacinto
e4fa894153
fix(llama.cpp): correctly handle embeddings in batches () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-07 19:29:52 +01:00
Ettore Di Giacinto
69caccfa82
chore(model gallery): add granite embeddings models () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-06 23:17:40 +01:00
Ettore Di Giacinto
ab50c13160
chore(model gallery): add nomic-embed-text-v1.5 () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-06 23:10:39 +01:00
LocalAI [bot]
56d4e82b14
chore: ⬆️ Update ggml-org/llama.cpp to 3d652bfddfba09022525067e672c3c145c074649 () 
⬆️ Update ggml-org/llama.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2025-03-06 21:54:14 +00:00
Ettore Di Giacinto
09b5bd48bc
chore(model gallery): add rombo-org_rombo-llm-v3.1-qwq-32b () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-06 10:42:45 +01:00
Ettore Di Giacinto
957dcfb6a9
chore(model gallery): add qwen_qwq-32b () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-06 10:28:03 +01:00
Ettore Di Giacinto
67f7bffd18
chore(deps): update llama.cpp and sync with upstream changes () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-06 00:40:58 +01:00
Ettore Di Giacinto
de81b42b49
feat(ui): remove api key handling and small ui adjustments () 
* chore(ui): drop set api key button

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

* chore(ui): shore in-progress installs in model view

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

* feat(ui): improve text to image view

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-05 19:37:36 +01:00
Ettore Di Giacinto
06eb7e9fa7
chore(model gallery): add llama-3.3-magicalgirl-2.5-i1 () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-05 09:35:48 +01:00
Ettore Di Giacinto
45bc1ac566
chore(model gallery): add lolzinventor_meta-llama-3.1-8b-survivev3 () 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2025-03-05 09:33:41 +01:00