Commit Graph

1844 Commits

Author SHA1 Message Date
Ettore Di Giacinto
d65c16e364 debug 2024-06-14 08:42:15 +02:00
LocalAI [bot]
25f45827ab
⬆️ Update ggerganov/whisper.cpp (#2565)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-14 00:26:51 +00:00
LocalAI [bot]
f322f7c62d
⬆️ Update ggerganov/llama.cpp (#2564)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-13 23:47:50 +00:00
Ettore Di Giacinto
06351cbbb4
feat(binary): support extracted bundled libs on darwin (#2563)
When offering fallback libs, use the proper env var for darwin

Note: this does not include the libraries itself, but only sets the
proper env var for the libs to be picked up on darwin.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-13 22:59:42 +02:00
Ettore Di Giacinto
8f952d90b0
feat(guesser): identify gemma models (#2561)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-13 19:12:37 +02:00
Ettore Di Giacinto
7b205510f9
feat(gallery): uniform download from CLI (#2559)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-13 16:12:46 +02:00
LocalAI [bot]
f183fec232
⬆️ Update ggerganov/llama.cpp (#2554)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-13 08:34:32 +00:00
Ettore Di Giacinto
91f48b2143
docs(gallery): lazy-load images (#2557)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-13 01:05:24 +02:00
Ettore Di Giacinto
f404580256 docs: bump go version
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-13 00:49:51 +02:00
Ettore Di Giacinto
882556d4db
feat(gallery): show available models in website, allow local-ai models install to install from galleries (#2555)
* WIP

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

* gen a static page instead (we force DNS redirects to it)

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

* feat(gallery): install models from CLI, unify install

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

* Uniform graphic of model page

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

* Makefile: update targets

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

* Slightly enhance gallery view

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

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-13 00:47:16 +02:00
LocalAI [bot]
f8382adbf7
⬆️ Update ggerganov/llama.cpp (#2551)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-12 08:54:00 +00:00
LocalAI [bot]
80298f94fa
⬆️ Update ggerganov/whisper.cpp (#2552)
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
2024-06-12 07:39:21 +00:00
Ettore Di Giacinto
0f8b489346
models(gallery): add badger-lambda-llama-3-8b (#2550)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-11 19:11:42 +02:00
Ettore Di Giacinto
154694462e
models(gallery): add duloxetine (#2549)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-11 19:06:26 +02:00
Ettore Di Giacinto
347317d5d2
models(gallery): add average_normie_v3.69_8b-iq-imatrix (#2548)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
2024-06-11 19:05:27 +02:00
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