dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 10:35:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21
3455 commits 54 branches 113 tags 41 MiB
Commit graph

3455 commits

This branch
This branch
All branches
Author SHA1 Message Date
LocalAI [bot]
bc8dd3ad14
chore: ⬆️ Update ggerganov/llama.cpp to 2cd43f4900ba0e34124fdcbf02a7f9df25a10a3d (#4491) 
⬆️ Update ggerganov/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>
 2024-12-24 21:44:11 +00:00
Ettore Di Giacinto
b969053701
chore(gallery): re-order 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-12-24 11:10:56 +01:00
Ettore Di Giacinto
60bf7c9dd7
chore(model gallery): add rombos-llm-70b-llama-3.3 (#4490) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-24 11:04:31 +01:00
Ettore Di Giacinto
d65c10cee7
chore(model gallery): add tqwendo-36b (#4489) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-24 11:04:19 +01:00
Ettore Di Giacinto
6c71698299
chore(model gallery): add l3.3-ms-evalebis-70b (#4488) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-24 10:59:36 +01:00
LocalAI [bot]
c7c275c7c8
chore(model-gallery): ⬆️ update checksum (#4487) 
⬆️ 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>
 2024-12-24 10:56:02 +01:00
LocalAI [bot]
d0adbee75d
chore: ⬆️ Update ggerganov/llama.cpp to 32d6ee6385b3fc908b283f509b845f757a6e7206 (#4486) 
⬆️ Update ggerganov/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>
 2024-12-24 10:55:30 +01:00
dependabot[bot]
159a7f6df2
chore(deps): Bump docs/themes/hugo-theme-relearn from bd1f3d3 to ec88e24 (#4460) 
chore(deps): Bump docs/themes/hugo-theme-relearn

Bumps [docs/themes/hugo-theme-relearn](https://github.com/McShelby/hugo-theme-relearn) from `bd1f3d3` to `ec88e24`.
- [Release notes](https://github.com/McShelby/hugo-theme-relearn/releases)
- [Commits](bd1f3d3432...ec88e24f46)

---
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>
 2024-12-23 22:15:38 +00:00
Ettore Di Giacinto
0eb2911aad
chore(llava): update clip.patch (#4453) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-23 19:11:31 +01:00
Ettore Di Giacinto
cab9f88ca4
chore(docs): add nvidia l4t instructions (#4454) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-23 18:59:33 +01:00
Ettore Di Giacinto
a3b675b09e
Delete .cirrus.yml 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-12-23 18:31:50 +01:00
Ettore Di Giacinto
6477913e8f
chore(ci): increase task timeout 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-12-23 16:43:32 +01:00
Ettore Di Giacinto
138cd97ce7 chore(ci): try to add CirrusCI to build arm64 images natively 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-23 15:37:57 +01:00
Ettore Di Giacinto
4dd9ac39b0
chore(ci): comment arm64 job until we find a native CI runner (#4452) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-23 12:34:39 +01:00
LocalAI [bot]
23499ddc8a
chore: ⬆️ Update ggerganov/llama.cpp to ebdee9478ca7ba65497b9b96f7457698c6ee5115 (#4451) 
⬆️ Update ggerganov/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>
 2024-12-22 22:56:41 +00:00
Ettore Di Giacinto
8864156300
chore(nvidia-l4t): add l4t arm64 images (#4449) 
chore(nvidia-l4t): add nvidia-l4t arm64 images

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-22 21:29:33 +01:00
Ettore Di Giacinto
478014ca18
feat(Dockerfile): allow to skip driver installation (#4447) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-22 21:28:38 +01:00
Ettore Di Giacinto
d45477b003
chore(model gallery): add llama-3.3-70b-instruct-ablated (#4448) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-22 08:38:47 +01:00
Ettore Di Giacinto
396fb88e33
chore(model gallery): add anubis-70b-v1 (#4446) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-22 08:33:35 +01:00
LocalAI [bot]
a429ec1b3f
chore: ⬆️ Update ggerganov/llama.cpp to 5cd85b5e008de2ec398d6596e240187d627561e3 (#4445) 
⬆️ Update ggerganov/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>
 2024-12-21 21:44:44 +00:00
Ettore Di Giacinto
5b5fb9c22a
chore(model gallery): add orca_mini_v8_1_70b (#4444) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-21 10:39:58 +01:00
LocalAI [bot]
801a87c3a6
chore: ⬆️ Update ggerganov/llama.cpp to eb5c3dc64bd967f2e23c87d9dec195f45468de60 (#4442) 
⬆️ Update ggerganov/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>
 2024-12-20 21:48:03 +00:00
Ettore Di Giacinto
badbd212f7
chore(model gallery): add tq2.5-14b-neon-v1 (#4441) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-20 16:11:16 +01:00
Ettore Di Giacinto
c4bbecc4d6
chore(model gallery): add tq2.5-14b-aletheia-v1 (#4440) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-20 16:08:23 +01:00
Ettore Di Giacinto
8a08e9ec67
fix(openvoice): pin numpy before installing torch (#4439) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-20 10:34:23 +01:00
LocalAI [bot]
61e486dbf5
chore: ⬆️ Update ggerganov/llama.cpp to d408bb9268a988c5a60a5746d3a6430386e7604d (#4437) 
⬆️ Update ggerganov/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>
 2024-12-19 23:03:47 +00:00
Ettore Di Giacinto
f2f387e1dd
fix(openvoice): do not pin numpy (#4438) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-19 21:30:43 +01:00
Ettore Di Giacinto
3be9a08fc9
fix(deps): pin openvoice pytorch/torchaudio (#4436) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-19 18:24:33 +01:00
Ettore Di Giacinto
b325807c60
fix(intel): pin torch and intel-extensions (#4435) 
* fix(intel): pin torch version

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

* fix(intel): pin intel packages version

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-19 15:39:32 +01:00
jtwolfe
ae9855a39e
chore(docs): patch p2p detail in env and docs (#4434) 
* Update distributed_inferencing.md

Signed-off-by: jtwolfe <jamie.t.wolfe@gmail.com>

* Update .env

Signed-off-by: jtwolfe <jamie.t.wolfe@gmail.com>

* Update distributed_inferencing.md

whoops

Signed-off-by: jtwolfe <jamie.t.wolfe@gmail.com>

---------

Signed-off-by: jtwolfe <jamie.t.wolfe@gmail.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-12-19 15:19:31 +01:00
LocalAI [bot]
9ac62b589f
chore: ⬆️ Update ggerganov/llama.cpp to cd920d0ac38ec243605a5a57c50941140a193f9e (#4433) 
⬆️ Update ggerganov/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>
 2024-12-19 12:15:30 +00:00
Ettore Di Giacinto
d12660a286
chore(model gallery): add llama-chat-summary-3.2-3b (#4432) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-19 09:56:19 +01:00
LocalAI [bot]
3d3bd2d10f
chore: ⬆️ Update ggerganov/llama.cpp to 0bf2d10c5514ff61b99897a4a5054f846e384e1e (#4429) 
⬆️ Update ggerganov/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>
 2024-12-19 09:53:49 +01:00
Ettore Di Giacinto
b656d10556
chore(model gallery): add llama-song-stream-3b-instruct (#4431) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-19 09:48:33 +01:00
Ettore Di Giacinto
8c67f38ef6
chore(model gallery): add falcon3-10b-instruct (#4426) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-18 10:36:41 +01:00
Ettore Di Giacinto
4623728cd7
chore(model gallery): add qwen2-vl-72b-instruct (#4425) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-18 10:35:49 +01:00
Ettore Di Giacinto
5f804aa6e8
chore(model gallery): add falcon3-3b-instruct (#4424) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-18 10:32:31 +01:00
Ettore Di Giacinto
f52c6e3a31
chore(model gallery): add falcon3-1b-instruct (#4423) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-18 10:12:06 +01:00
Ettore Di Giacinto
0b4bb7a562
chore(model gallery): add llama-openreviewer-8b (#4422) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-18 09:49:48 +01:00
mintyleaf
2bc4b56a79
feat: stream tokens usage (#4415) 
* Use pb.Reply instead of []byte with Reply.GetMessage() in llama grpc to get the proper usage data in reply streaming mode at the last [DONE] frame

* Fix 'hang' on empty message from the start

Seems like that empty message marker trick was unnecessary

---------

Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-12-18 09:48:50 +01:00
LocalAI [bot]
fc920cc58a
chore: ⬆️ Update ggerganov/llama.cpp to 081b29bd2a3d91e7772e3910ce223dd63b8d7d26 (#4421) 
⬆️ Update ggerganov/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>
 2024-12-17 22:15:14 +00:00
Ettore Di Giacinto
fdb560b8e5
chore(model gallery): add qwq-lcot-7b-instruct (#4419) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-17 10:10:37 +01:00
Ettore Di Giacinto
708cba0c1b
chore(llama.cpp): bump, drop penalize_nl (#4418) 
deps(llama.cpp): bump, drop penalize_nl

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-17 00:47:52 +01:00
Ettore Di Giacinto
24abf568cb
chore(tests): stabilize tts test (#4417) 
chore(tests): stabilize test

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-17 00:46:48 +01:00
Ettore Di Giacinto
7ca0e2d925
fix(python): remove pin to setuptools, pin python version (#4395) 
fix(setuptools): remove pin

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-16 10:55:02 +01:00
Ettore Di Giacinto
037e8030bf
chore(model gallery): add qwen2-7b-multilingual-rp (#4394) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-16 09:48:33 +01:00
Ettore Di Giacinto
472d11f884
chore(model gallery): add marco-o1-uncensored (#4393) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-16 09:48:23 +01:00
Ettore Di Giacinto
b40d5d12b7
chore(model gallery): add naturallm-7b-instruct (#4392) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-12-16 09:47:49 +01:00
LocalAI [bot]
6938618e30
chore: ⬆️ Update ggerganov/llama.cpp to a0974156f334acf8af5858d7ede5ab7d7490d415 (#4391) 
⬆️ Update ggerganov/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>
 2024-12-15 22:01:44 +00:00
Ettore Di Giacinto
5d9c530eaa
fix(gallery): disable default embeddings 
Do not always enable embeddings on llama32, but let specific models settings

Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-12-15 18:43:39 +01:00