ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2024-12-25 23:31:04 +00:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity
2,129 Commits 43 Branches 108 Tags 51 MiB
53f90218b0
Commit Graph

2129 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Ettore Di Giacinto
d40722d2fa
models(gallery): add llama-salad-8x8b (#2547) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-11 18:40:16 +02:00
Ettore Di Giacinto
7b12300f15
models(gallery): add l3-aethora-15b (#2546) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-11 18:31:13 +02:00
Ettore Di Giacinto
3c50abffdd
models(gallery): add hathor-l3-8b-v.01-iq-imatrix (#2545) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-11 16:37:27 +02:00
Ettore Di Giacinto
2eb2ed84ab
models(gallery): add llama3-8B-aifeifei-1.2-iq-imatrix (#2544) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-11 10:54:21 +02:00
LocalAI [bot]
5da10fb769
⬆️ Update ggerganov/llama.cpp (#2540) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-11 00:59:17 +00:00
LocalAI [bot]
bec883e3ff
⬆️ Update ggerganov/whisper.cpp (#2539) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-10 23:32:32 +00:00
Ettore Di Giacinto
14b41be057
feat(detection): detect by template in gguf file, add qwen2, phi, mistral and chatml (#2536) 
feat(detection): detect by template in gguf file, add qwen and chatml

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-10 22:58:04 +02:00
reid41
aff2acacf9
Add integrations (#2535) 
* update integrations

* update integrations1
 2024-06-10 19:18:47 +02:00
Rene Leonhardt
b4d4c0a18f
chore(deps): Update Dockerfile (#2532) 
Signed-off-by: Rene Leonhardt <65483435+reneleonhardt@users.noreply.github.com>
 2024-06-10 08:40:02 +00:00
LocalAI [bot]
3a5f2283ea
⬆️ Update ggerganov/llama.cpp (#2531) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-09 23:15:59 +00:00
Ettore Di Giacinto
d9109ffafb
feat(defaults): add defaults for Command-R models (#2529) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-09 20:00:16 +02:00
Ettore Di Giacinto
d7e137295a
feat(util): add util command to print GGUF informations (#2528) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-09 19:27:42 +02:00
Ettore Di Giacinto
6c087ae743
feat(arm64): enable single-binary builds (#2490) 
* ci: try to build for arm64

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

* Allow to skip hipblas on make dist

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

* use arm64 cross compiler

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

* correctly target go arm64

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

* create a separate target

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

* cross-compile grpc

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

* Add Protobuf include dirs

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

* temp disable CUDA build

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

* aarch64 builds: Reduce backends

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

* Even less backends

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

* Even less backends

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

* feat(startup): allow to load libs from extracted assets

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

* makefile: set arch

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-09 15:11:37 +02:00
LocalAI [bot]
88af1033d6
⬆️ Update ggerganov/llama.cpp (#2524) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-08 23:53:35 +00:00
Ettore Di Giacinto
e96d2d7667
feat(ui): add page to talk with voice, transcription, and tts (#2520) 
* feat(ui): add page to talk with voice, transcription, and tts

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

* Enhance graphics and status reporting

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

* Better UX by blocking unvalid actions

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-09 00:03:26 +02:00
Ettore Di Giacinto
aae7ad9d73
feat(llama.cpp): guess model defaults from file (#2522) 
* wip: guess informations from gguf file

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

* update go mod

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

* Small fixups

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

* Identify llama3

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

* Do not try to guess the name, as reading gguf files can be expensive

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

* Allow to disable guessing

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-08 22:13:02 +02:00
LocalAI [bot]
23b3d22525
⬆️ Update ggerganov/llama.cpp (#2518) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-07 23:35:16 +00:00
Ettore Di Giacinto
603d81dda1
feat(install): add install.sh for quick installs (#2489) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-07 22:30:41 +02:00
LocalAI [bot]
a21a52d384
models(gallery): ⬆️ update checksum (#2519) 
⬆️ 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>
 2024-06-07 22:17:25 +02:00
Dave
219078a5e0
test: e2e /reranker endpoint (#2211) 
Create a simple e2e test for the /reranker api \\ go mod tidy

Signed-off-by: Dave Lee <dave@gray101.com>
 2024-06-07 18:45:52 +00:00
Ettore Di Giacinto
3b7a78adda
fix(stream): do not break channel consumption (#2517) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-07 17:20:42 +02:00
Sertaç Özercan
0d62594099
fix: fix chat webui response parsing (#2515) 
fix: fix chat webui

Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
 2024-06-07 17:20:31 +02:00
Dave
d38e9090df
experiment: -j4 for build-linux: (#2514) 
experiment: set -j4 to see if things go faster, while we wait for a proper fix from mudler

Signed-off-by: Dave Lee <dave@gray101.com>
 2024-06-07 11:22:28 +02:00
Ettore Di Giacinto
b049805c9b
ci: run release build on self-hosted runners (#2505) 2024-06-06 22:16:34 -04:00
LocalAI [bot]
0f9b58f2cf
⬆️ Update ggerganov/llama.cpp (#2508) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-06 23:48:17 +00:00
LocalAI [bot]
0f134d557e
⬆️ Update ggerganov/whisper.cpp (#2507) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-06 23:21:25 +00:00
Ettore Di Giacinto
2676e127ae
models(gallery): add llama3-8b-feifei-1.0-iq-imatrix (#2511) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-07 00:17:59 +02:00
Ettore Di Giacinto
270d4f8413
models(gallery): add rawr_llama3_8b-iq-imatrix (#2510) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-07 00:12:11 +02:00
Ettore Di Giacinto
2d79cee8cb
models(gallery): add llama3-8B-aifeifei-1.0-iq-imatrix (#2509) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-07 00:07:20 +02:00
Ettore Di Giacinto
4c9623f50d
deps(whisper): update, add libcufft-dev (#2501) 
* arrow_up: Update ggerganov/whisper.cpp

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>

* fix(build): add libcufft-dev

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>
 2024-06-06 08:41:04 +02:00
Ettore Di Giacinto
596cf76135
build(intel): bundle intel variants in single-binary (#2494) 
* wip: try to build also intel variants

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

* Add dependencies

* Select automatically intel backend

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-06 08:40:51 +02:00
LocalAI [bot]
a293aa1b79
⬆️ Update ggerganov/llama.cpp (#2493) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-06 00:02:51 +00:00
Ettore Di Giacinto
c4eb02c80f
models(gallery): add l3-8b-stheno-v3.2-iq-imatrix (#2500) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-05 23:46:59 +02:00
Ettore Di Giacinto
9c9198ff08
models(gallery): add Llama-3-Yggdrasil-2.0-8B (#2499) 
models(gallery): add Llama-3-Yggdrasil-2.0-8B-GGUF

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-05 23:42:23 +02:00
Ettore Di Giacinto
83c79d5453
models(gallery): add llama-3-instruct-8b-SimPO-ExPO (#2498) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-05 23:37:59 +02:00
Ettore Di Giacinto
88fd000065
models(gallery): add phi-3-4x4b (#2497) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-05 23:29:15 +02:00
Ettore Di Giacinto
956d652314
models(gallery): add nyun (#2496) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-05 23:22:58 +02:00
Ettore Di Giacinto
9ce2b4d71f
models(gallery): add dolphin-2.9.2-phi-3-Medium-abliterated (#2495) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-05 23:14:43 +02:00
Ettore Di Giacinto
4e974cb4fc
models(gallery): add dolphin-2.9.2-Phi-3-Medium (#2492) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-05 19:17:20 +02:00
Dave
d072835796
feat:OpaqueErrors to hide error information (#2486) 
* adds a new configuration option to hide all error message information from http requests
---------

Signed-off-by: Dave Lee <dave@gray101.com>
 2024-06-05 08:45:24 +02:00
Ettore Di Giacinto
17cf6c4a4d
feat(amdgpu): try to build in single binary (#2485) 
* feat(amdgpu): try to build in single binary

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

* Release space from worker

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-05 08:44:15 +02:00
LocalAI [bot]
fab3e711ff
⬆️ Update ggerganov/llama.cpp (#2487) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-04 23:11:28 +00:00
Dave
4e1463fec2
feat: fiber CSRF (#2482) 
new config option - enables or disables the fiber csrf middleware

Signed-off-by: Dave Lee <dave@gray101.com>
 2024-06-04 19:43:46 +00:00
Dave
2fc6fe806b
fix: pkg/downloader should respect basePath for file:// urls (#2481) 
* pass basePath down to pkg/downloader

Signed-off-by: Dave Lee <dave@gray101.com>

* enforce

Signed-off-by: Dave Lee <dave@gray101.com>

---------

Signed-off-by: Dave Lee <dave@gray101.com>
 2024-06-04 14:32:47 +00:00
Ettore Di Giacinto
bdd6769b2d
feat(default): use number of physical cores as default (#2483) 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
 2024-06-04 15:23:29 +02:00
Ettore Di Giacinto
1ffee9989f
README: update sponsors list (#2476) 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-06-04 15:23:00 +02:00
Dave
34ab442ce9
toil: bump grpc version (#2480) 
bump the grpc package version

---------

Signed-off-by: Dave Lee <dave@gray101.com>
 2024-06-04 08:39:19 +02:00
LocalAI [bot]
67aa31faad
⬆️ Update ggerganov/llama.cpp (#2477) 
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
 2024-06-03 23:09:24 +00:00
fakezeta
6ef78ef7f6
bugfix: CUDA acceleration not working (#2475) 
* bugfix: CUDA acceleration not working

CUDA not working after #2286.
Refactored the code to be more polish

* Update requirements.txt

Missing imports

Signed-off-by: fakezeta <fakezeta@gmail.com>

* Update requirements.txt

Signed-off-by: fakezeta <fakezeta@gmail.com>

---------

Signed-off-by: fakezeta <fakezeta@gmail.com>
 2024-06-03 22:41:42 +02:00
Ettore Di Giacinto
daa7544d9c
Update README.md 
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
 2024-06-03 19:55:01 +02:00